net/tun: implement ndo_set_rx_headroom

ndo_set_rx_headroom controls the align value used by tun devices to
allocate skbs on frame reception.
When the xmit device adds a large encapsulation, this avoids an skb
head reallocation on forwarding.

The measured improvement when forwarding towards a vxlan dev with
frame size below the egress device MTU is as follow:

vxlan over ipv6, bridged: +6%
vxlan over ipv6, ovs: +7%

In case of ipv4 tunnels there is no improvement, since the tun
device default alignment provides enough headroom to avoid the skb
head reallocation.

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

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 88bb8cc3555b8c8197d7993a2a9c338ddab8e8b1..afdf950617c36e0bc5042da9cf0e57a0cb0cd88d 100644 (file)
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -187,6 +187,7 @@ struct tun_struct {
 #define TUN_USER_FEATURES (NETIF_F_HW_CSUM|NETIF_F_TSO_ECN|NETIF_F_TSO| \
                          NETIF_F_TSO6|NETIF_F_UFO)
 
+       int                     align;
        int                     vnet_hdr_sz;
        int                     sndbuf;
        struct tap_filter       txflt;
@@ -934,6 +935,17 @@ static void tun_poll_controller(struct net_device *dev)
        return;
 }
 #endif
+
+static void tun_set_headroom(struct net_device *dev, int new_hr)
+{
+       struct tun_struct *tun = netdev_priv(dev);
+
+       if (new_hr < NET_SKB_PAD)
+               new_hr = NET_SKB_PAD;
+
+       tun->align = new_hr;
+}
+
 static const struct net_device_ops tun_netdev_ops = {
        .ndo_uninit             = tun_net_uninit,
        .ndo_open               = tun_net_open,
@@ -945,6 +957,7 @@ static const struct net_device_ops tun_netdev_ops = {
 #ifdef CONFIG_NET_POLL_CONTROLLER
        .ndo_poll_controller    = tun_poll_controller,
 #endif
+       .ndo_set_rx_headroom    = tun_set_headroom,
 };
 
 static const struct net_device_ops tap_netdev_ops = {
@@ -962,6 +975,7 @@ static const struct net_device_ops tap_netdev_ops = {
        .ndo_poll_controller    = tun_poll_controller,
 #endif
        .ndo_features_check     = passthru_features_check,
+       .ndo_set_rx_headroom    = tun_set_headroom,
 };
 
 static void tun_flow_init(struct tun_struct *tun)
@@ -1086,7 +1100,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
        struct tun_pi pi = { 0, cpu_to_be16(ETH_P_IP) };
        struct sk_buff *skb;
        size_t total_len = iov_iter_count(from);
-       size_t len = total_len, align = NET_SKB_PAD, linear;
+       size_t len = total_len, align = tun->align, linear;
        struct virtio_net_hdr gso = { 0 };
        int good_linear;
        int copylen;
@@ -1694,6 +1708,7 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
                tun->txflt.count = 0;
                tun->vnet_hdr_sz = sizeof(struct virtio_net_hdr);
 
+               tun->align = NET_SKB_PAD;
                tun->filter_attached = false;
                tun->sndbuf = tfile->socket.sk->sk_sndbuf;