packet: vnet_hdr support for tpacket_rcv

Support socket option PACKET_VNET_HDR together with PACKET_RX_RING.
When enabled, a struct virtio_net_hdr will precede the data in the
packet ring slots.

Verified with test program at
github.com/wdebruij/kerneltools/blob/master/tests/psock_rxring_vnet.c

  pkt: 1454269209.798420 len=5066
  vnet: gso_type=tcpv4 gso_size=1448 hlen=66 ecn=off
  csum: start=34 off=16
  eth: proto=0x800
  ip: src=<masked> dst=<masked> proto=6 len=5052

Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index bd3de7b..b26df32 100644 (file)
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2206,7 +2206,9 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
                unsigned int maclen = skb_network_offset(skb);
                netoff = TPACKET_ALIGN(po->tp_hdrlen +
                                       (maclen < 16 ? 16 : maclen)) +
-                       po->tp_reserve;
+                                      po->tp_reserve;
+               if (po->has_vnet_hdr)
+                       netoff += sizeof(struct virtio_net_hdr);
                macoff = netoff - maclen;
        }
        if (po->tp_version <= TPACKET_V2) {
@@ -2243,7 +2245,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
        h.raw = packet_current_rx_frame(po, skb,
                                        TP_STATUS_KERNEL, (macoff+snaplen));
        if (!h.raw)
-               goto ring_is_full;
+               goto drop_n_account;
        if (po->tp_version <= TPACKET_V2) {
                packet_increment_rx_head(po, &po->rx_ring);
        /*
@@ -2262,6 +2264,14 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
        }
        spin_unlock(&sk->sk_receive_queue.lock);
 
+       if (po->has_vnet_hdr) {
+               if (__packet_rcv_vnet(skb, h.raw + macoff -
+                                          sizeof(struct virtio_net_hdr))) {
+                       spin_lock(&sk->sk_receive_queue.lock);
+                       goto drop_n_account;
+               }
+       }
+
        skb_copy_bits(skb, 0, h.raw + macoff, snaplen);
 
        if (!(ts_status = tpacket_get_timestamp(skb, &ts, po->tp_tstamp)))
@@ -2357,7 +2367,7 @@ drop:
        kfree_skb(skb);
        return 0;
 
-ring_is_full:
+drop_n_account:
        po->stats.stats1.tp_drops++;
        spin_unlock(&sk->sk_receive_queue.lock);
 
@@ -3587,7 +3597,8 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
                }
                if (optlen < len)
                        return -EINVAL;
-               if (pkt_sk(sk)->has_vnet_hdr)
+               if (pkt_sk(sk)->has_vnet_hdr &&
+                   optname == PACKET_TX_RING)
                        return -EINVAL;
                if (copy_from_user(&req_u.req, optval, len))
                        return -EFAULT;