ovs: propagate per dp max headroom to all vports

This patch implements bookkeeping support to compute the maximum
headroom for all the devices in each datapath. When said value
changes, the underlying devs are notified via the
ndo_set_rx_headroom method.

This also increases the internal vports xmit performance.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 53 insertions, 1 deletions

diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index c4e8455d5d56..e6a7d494df24 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -1908,6 +1908,29 @@ static struct vport *lookup_vport(struct net *net,
                 return ERR_PTR(-EINVAL);
 }
 
+/* Called with ovs_mutex */
+static void update_headroom(struct datapath *dp)
+{
+        unsigned dev_headroom, max_headroom = 0;
+        struct net_device *dev;
+        struct vport *vport;
+        int i;
+
+        for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++) {
+                hlist_for_each_entry_rcu(vport, &dp->ports[i], dp_hash_node) {
+                        dev = vport->dev;
+                        dev_headroom = netdev_get_fwd_headroom(dev);
+                        if (dev_headroom > max_headroom)
+                                max_headroom = dev_headroom;
+                }
+        }
+
+        dp->max_headroom = max_headroom;
+        for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++)
+                hlist_for_each_entry_rcu(vport, &dp->ports[i], dp_hash_node)
+                        netdev_set_rx_headroom(vport->dev, max_headroom);
+}
+
 static int ovs_vport_cmd_new(struct sk_buff *skb, struct genl_info *info)
 {
         struct nlattr **a = info->attrs;
@@ -1973,6 +1996,12 @@ restart:
 
         err = ovs_vport_cmd_fill_info(vport, reply, info->snd_portid,
                                       info->snd_seq, 0, OVS_VPORT_CMD_NEW);
+
+        if (netdev_get_fwd_headroom(vport->dev) > dp->max_headroom)
+                update_headroom(dp);
+        else
+                netdev_set_rx_headroom(vport->dev, dp->max_headroom);
+
         BUG_ON(err < 0);
         ovs_unlock();
 
@@ -2039,8 +2068,10 @@ exit_unlock_free:
 
 static int ovs_vport_cmd_del(struct sk_buff *skb, struct genl_info *info)
 {
+        bool must_update_headroom = false;
         struct nlattr **a = info->attrs;
         struct sk_buff *reply;
+        struct datapath *dp;
         struct vport *vport;
         int err;
 
@@ -2062,7 +2093,16 @@ static int ovs_vport_cmd_del(struct sk_buff *skb, struct genl_info *info)
         err = ovs_vport_cmd_fill_info(vport, reply, info->snd_portid,
                                       info->snd_seq, 0, OVS_VPORT_CMD_DEL);
         BUG_ON(err < 0);
+
+        /* the vport deletion may trigger dp headroom update */
+        dp = vport->dp;
+        if (netdev_get_fwd_headroom(vport->dev) == dp->max_headroom)
+                must_update_headroom = true;
+        netdev_reset_rx_headroom(vport->dev);
         ovs_dp_detach_port(vport);
+
+        if (must_update_headroom)
+                update_headroom(dp);
         ovs_unlock();
 
         ovs_notify(&dp_vport_genl_family, reply, info);
diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h
index 67bdecd9fdc1..427e39a045cf 100644
--- a/net/openvswitch/datapath.h
+++ b/net/openvswitch/datapath.h
@@ -68,6 +68,8 @@ struct dp_stats_percpu {
  * ovs_mutex and RCU.
  * @stats_percpu: Per-CPU datapath statistics.
  * @net: Reference to net namespace.
+ * @max_headroom: the maximum headroom of all vports in this datapath; it will
+ * be used by all the internal vports in this dp.
  *
  * Context: See the comment on locking at the top of datapath.c for additional
  * locking information.
@@ -89,6 +91,8 @@ struct datapath {
         possible_net_t net;
 
         u32 user_features;
+
+        u32 max_headroom;
 };
 
 /**
diff --git a/net/openvswitch/vport-internal_dev.c b/net/openvswitch/vport-internal_dev.c
index ec76398a792f..83a5534abd31 100644
--- a/net/openvswitch/vport-internal_dev.c
+++ b/net/openvswitch/vport-internal_dev.c
@@ -138,6 +138,11 @@ internal_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
         return stats;
 }
 
+void internal_set_rx_headroom(struct net_device *dev, int new_hr)
+{
+        dev->needed_headroom = new_hr;
+}
+
 static const struct net_device_ops internal_dev_netdev_ops = {
         .ndo_open = internal_dev_open,
         .ndo_stop = internal_dev_stop,
@@ -145,6 +150,7 @@ static const struct net_device_ops internal_dev_netdev_ops = {
         .ndo_set_mac_address = eth_mac_addr,
         .ndo_change_mtu = internal_dev_change_mtu,
         .ndo_get_stats64 = internal_get_stats,
+        .ndo_set_rx_headroom = internal_set_rx_headroom,
 };
 
 static struct rtnl_link_ops internal_dev_link_ops __read_mostly = {
@@ -158,7 +164,8 @@ static void do_setup(struct net_device *netdev)
         netdev->netdev_ops = &internal_dev_netdev_ops;
 
         netdev->priv_flags &= ~IFF_TX_SKB_SHARING;
-        netdev->priv_flags |= IFF_LIVE_ADDR_CHANGE | IFF_OPENVSWITCH;
+        netdev->priv_flags |= IFF_LIVE_ADDR_CHANGE | IFF_OPENVSWITCH |
+                              IFF_PHONY_HEADROOM;
         netdev->destructor = internal_dev_destructor;
         netdev->ethtool_ops = &internal_dev_ethtool_ops;
         netdev->rtnl_link_ops = &internal_dev_link_ops;
@@ -199,6 +206,7 @@ static struct vport *internal_dev_create(const struct vport_parms *parms)
                 err = -ENOMEM;
                 goto error_free_netdev;
         }
+        vport->dev->needed_headroom = vport->dp->max_headroom;
 
         dev_net_set(vport->dev, ovs_dp_get_net(vport->dp));
         internal_dev = internal_dev_priv(vport->dev);