If an L3 RX handler has been set for the current skb device then the skb is run through the NF_HOOK for NF_INET_PRE_ROUTING with a dummy function to not further process the packet. From there the skb is passed to the L3 RX handler. The L3 RX handler maintains the same semantics as the current RX handler -- it can modify the skb and ask for another pass, consume it or just ignore the packet and have it continue on.
Signed-off-by: David Ahern <d...@cumulusnetworks.com> --- net/ipv4/ip_input.c | 32 ++++++++++++++++++++++++++++++-- 1 file changed, 30 insertions(+), 2 deletions(-) diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index f4fc8a77aaa7..75da9dc0e8f5 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -372,11 +372,17 @@ static int ip_rcv_finish(struct sock *sk, struct sk_buff *skb) return NET_RX_DROP; } +static int ip_rcv_first_pass(struct sock *sk, struct sk_buff *skb) +{ + return 0; +} + /* * Main IP Receive routine. */ int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { + rx_handler_func_t *rx_handler; const struct iphdr *iph; u32 len; @@ -386,6 +392,8 @@ int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, if (skb->pkt_type == PACKET_OTHERHOST) goto drop; +another_round: + rx_handler = rcu_dereference(skb->dev->l3_rx_handler); IP_UPD_PO_STATS_BH(dev_net(dev), IPSTATS_MIB_IN, skb->len); @@ -453,9 +461,29 @@ int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, /* Must drop socket now because of tproxy. */ skb_orphan(skb); + if (rx_handler) { + int rc; + + rc = NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, NULL, skb, + dev, NULL, ip_rcv_first_pass); + if (rc != 0) + return rc; + + switch (rx_handler(&skb)) { + case RX_HANDLER_CONSUMED: + return 0; + case RX_HANDLER_ANOTHER: + rx_handler = NULL; + goto another_round; + case RX_HANDLER_PASS: + return ip_rcv_finish(NULL, skb); + default: + pr_err("Invalid return for L3 rx_handler\n"); + } + } + return NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, NULL, skb, - dev, NULL, - ip_rcv_finish); + dev, NULL, ip_rcv_finish); csum_error: IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_CSUMERRORS); -- 1.9.1 -- To unsubscribe from this list: send the line "unsubscribe netdev" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html