[PATCH 1/1] RDMA/rxe: Fetch skb packets from ethernet layer

[Zhu Yanjun <yanjunz@nvidia.com>]

In the original design, in rx, skb packet would pass ethernet
layer and IP layer, eventually reach udp tunnel.

Now rxe fetches the skb packets from the ethernet layer directly.
So this bypasses the IP and UDP layer. As such, the skb packets
are sent to the upper protocals directly from the ethernet layer.

This increases bandwidth and decreases latency.

Signed-off-by: Zhu Yanjun <yanjunz@nvidia.com>
---
 drivers/infiniband/sw/rxe/rxe_net.c |   45 ++++++++++++++++++++++++++++++++++-
 1 files changed, 44 insertions(+), 1 deletions(-)

diff --git a/drivers/infiniband/sw/rxe/rxe_net.c b/drivers/infiniband/sw/rxe/rxe_net.c
index 2e490e5..8ea68b6 100644
--- a/drivers/infiniband/sw/rxe/rxe_net.c
+++ b/drivers/infiniband/sw/rxe/rxe_net.c
@@ -18,6 +18,7 @@
 #include "rxe_loc.h"
 
 static struct rxe_recv_sockets recv_sockets;
+static struct net_device *g_ndev;
 
 struct device *rxe_dma_device(struct rxe_dev *rxe)
 {
@@ -113,7 +114,7 @@ static int rxe_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
 	}
 
 	tnl_cfg.encap_type = 1;
-	tnl_cfg.encap_rcv = rxe_udp_encap_recv;
+	tnl_cfg.encap_rcv = NULL;
 
 	/* Setup UDP tunnel */
 	setup_udp_tunnel_sock(net, sock, &tnl_cfg);
@@ -357,6 +358,38 @@ struct sk_buff *rxe_init_packet(struct rxe_dev *rxe, struct rxe_av *av,
 	return rxe->ndev->name;
 }
 
+static rx_handler_result_t rxe_handle_frame(struct sk_buff **pskb)
+{
+	struct sk_buff *skb = *pskb;
+	struct iphdr *iph;
+	struct udphdr *udph;
+
+	if (unlikely(skb->pkt_type == PACKET_LOOPBACK))
+		return RX_HANDLER_PASS;
+
+	if (!is_valid_ether_addr(eth_hdr(skb)->h_source)) {
+		kfree(skb);
+		return RX_HANDLER_CONSUMED;
+	}
+
+	if (eth_hdr(skb)->h_proto != cpu_to_be16(ETH_P_IP))
+		return RX_HANDLER_PASS;
+
+	iph = ip_hdr(skb);
+
+	if (iph->protocol != IPPROTO_UDP)
+		return RX_HANDLER_PASS;
+
+	udph = udp_hdr(skb);
+
+	if (udph->dest != cpu_to_be16(ROCE_V2_UDP_DPORT))
+		return RX_HANDLER_PASS;
+
+	rxe_udp_encap_recv(NULL, skb);
+
+	return RX_HANDLER_CONSUMED;
+}
+
 int rxe_net_add(const char *ibdev_name, struct net_device *ndev)
 {
 	int err;
@@ -367,6 +400,7 @@ int rxe_net_add(const char *ibdev_name, struct net_device *ndev)
 		return -ENOMEM;
 
 	rxe->ndev = ndev;
+	g_ndev = ndev;
 
 	err = rxe_add(rxe, ndev->mtu, ibdev_name);
 	if (err) {
@@ -374,6 +408,12 @@ int rxe_net_add(const char *ibdev_name, struct net_device *ndev)
 		return err;
 	}
 
+	rtnl_lock();
+	err = netdev_rx_handler_register(ndev, rxe_handle_frame, rxe);
+	rtnl_unlock();
+	if (err)
+		return err;
+
 	return 0;
 }
 
@@ -498,6 +538,9 @@ static int rxe_net_ipv6_init(void)
 
 void rxe_net_exit(void)
 {
+	rtnl_lock();
+	netdev_rx_handler_unregister(g_ndev);
+	rtnl_unlock();
 	rxe_release_udp_tunnel(recv_sockets.sk6);
 	rxe_release_udp_tunnel(recv_sockets.sk4);
 	unregister_netdevice_notifier(&rxe_net_notifier);
-- 
1.7.1