[ovs-dev] [PATCH v2] netdev-linux: do not send packets to down tap ifaces.

[Flavio Leitner]

Today OVS pushes packets to the TAP interface ignoring its
current state. That works because the kernel will return -EIO
when it's not UP and OVS will just ignore that as it is not
an OVS issue.

However, it causes a huge impact when broadcasts happen when
using userspace datapath accelerated with DPDK (e.g.: action
NORMAL).  This patch improves the situation by checking the
TAP's interface state before issueing any syscall.

However, there might be use-cases moving interfaces to other
networking namespaces and in that case, OVS can't retrieve
the iface state (sets it to DOWN). That would stop the traffic
breaking the use-case. This patch relies on netlink notifications
to find out if the device is local or not. When it's local, the
device state is checked otherwise it will behave as before.

Signed-off-by: Flavio Leitner <fbl at sysclose.org>
---
 lib/netdev-linux.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

ChangeLog:
V2 - drops are accounted.

diff --git a/lib/netdev-linux.c b/lib/netdev-linux.c
index 37143b8df..6dae7964a 100644
--- a/lib/netdev-linux.c
+++ b/lib/netdev-linux.c
@@ -502,6 +502,8 @@ struct netdev_linux {
 
     /* For devices of class netdev_tap_class only. */
     int tap_fd;
+    bool present;               /* If the device is present in the namespace */
+    uint64_t tx_dropped;        /* tap device can drop if the iface is down */
 };
 
 struct netdev_rxq_linux {
@@ -750,8 +752,10 @@ netdev_linux_update(struct netdev_linux *dev,
             dev->ifindex = change->if_index;
             dev->cache_valid |= VALID_IFINDEX;
             dev->get_ifindex_error = 0;
+            dev->present = true;
         } else {
             netdev_linux_changed(dev, change->ifi_flags, 0);
+            dev->present = false;
         }
     } else if (rtnetlink_type_is_rtnlgrp_addr(change->nlmsg_type)) {
         /* Invalidates in4, in6. */
@@ -1234,6 +1238,17 @@ netdev_linux_tap_batch_send(struct netdev *netdev_,
 {
     struct netdev_linux *netdev = netdev_linux_cast(netdev_);
     struct dp_packet *packet;
+
+    /* The Linux tap driver returns EIO if the device is not up,
+     * so if the device is not up, don't waste time sending it.
+     * However, if the device is in another network namespace
+     * then OVS can't retrieve the state. In that case, send the
+     * packets anyway. */
+    if (netdev->present && !(netdev->ifi_flags & IFF_UP)) {
+        netdev->tx_dropped += dp_packet_batch_size(batch);
+        return 0;
+    }
+
     DP_PACKET_BATCH_FOR_EACH (packet, batch) {
         size_t size = dp_packet_size(packet);
         ssize_t retval;
@@ -1825,6 +1840,7 @@ netdev_tap_get_stats(const struct netdev *netdev_, struct netdev_stats *stats)
         stats->multicast           += dev_stats.multicast;
         stats->collisions          += dev_stats.collisions;
     }
+    stats->tx_dropped += netdev->tx_dropped;
     ovs_mutex_unlock(&netdev->mutex);
 
     return error;
-- 
2.14.3