[PATCH net-next] udp: handle gro_receive only when necessary

[zhangliping]

From: zhangliping <zhanglipin...@baidu.com>

Under our udp pressure performance test, after gro is disabled, rx rate
will be improved from ~2500kpps to ~2800kpps. We can find some difference
from perf report:
1. gro is enabled:
  24.23%   [kernel]       [k] udp4_lib_lookup2
   5.42%   [kernel]       [k] __memcpy
   3.87%   [kernel]       [k] fib_table_lookup
   3.76%   [kernel]       [k] __netif_receive_skb_core
   3.68%   [kernel]       [k] ip_rcv

2. gro is disabled:
   9.66%   [kernel]       [k] udp4_lib_lookup2
   9.47%   [kernel]       [k] __memcpy
   4.75%   [kernel]       [k] fib_table_lookup
   4.71%   [kernel]       [k] __netif_receive_skb_core
   3.90%   [kernel]       [k] virtnet_poll

So if there's no udp tunnel(such as vxlan) configured, we can skip
the udp gro processing.

Signed-off-by: zhangliping <zhanglipin...@baidu.com>
---
 include/net/udp.h      |  2 ++
 net/ipv4/udp_offload.c |  7 +++++++
 net/ipv4/udp_tunnel.c  | 11 ++++++++++-
 3 files changed, 19 insertions(+), 1 deletion(-)

diff --git a/include/net/udp.h b/include/net/udp.h
index 6c759c8594e2..c503f8b06845 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -188,6 +188,8 @@ static inline struct udphdr *udp_gro_udphdr(struct sk_buff 
*skb)
        return uh;
 }
 
+extern struct static_key_false udp_gro_needed;
+
 /* hash routines shared between UDPv4/6 and UDP-Litev4/6 */
 static inline int udp_lib_hash(struct sock *sk)
 {
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 01801b77bd0d..9cb11a833964 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -10,10 +10,14 @@
  *     UDPv4 GSO support
  */
 
+#include <linux/static_key.h>
 #include <linux/skbuff.h>
 #include <net/udp.h>
 #include <net/protocol.h>
 
+DEFINE_STATIC_KEY_FALSE(udp_gro_needed);
+EXPORT_SYMBOL_GPL(udp_gro_needed);
+
 static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb,
        netdev_features_t features,
        struct sk_buff *(*gso_inner_segment)(struct sk_buff *skb,
@@ -250,6 +254,9 @@ struct sk_buff **udp_gro_receive(struct sk_buff **head, 
struct sk_buff *skb,
        int flush = 1;
        struct sock *sk;
 
+       if (!static_branch_unlikely(&udp_gro_needed))
+               goto out;
+
        if (NAPI_GRO_CB(skb)->encap_mark ||
            (skb->ip_summed != CHECKSUM_PARTIAL &&
             NAPI_GRO_CB(skb)->csum_cnt == 0 &&
diff --git a/net/ipv4/udp_tunnel.c b/net/ipv4/udp_tunnel.c
index 6539ff15e9a3..4a7b3c8223c0 100644
--- a/net/ipv4/udp_tunnel.c
+++ b/net/ipv4/udp_tunnel.c
@@ -1,4 +1,5 @@
 #include <linux/module.h>
+#include <linux/static_key.h>
 #include <linux/errno.h>
 #include <linux/socket.h>
 #include <linux/udp.h>
@@ -73,6 +74,9 @@ void setup_udp_tunnel_sock(struct net *net, struct socket 
*sock,
        udp_sk(sk)->gro_complete = cfg->gro_complete;
 
        udp_tunnel_encap_enable(sock);
+
+       if (udp_sk(sk)->gro_receive)
+               static_branch_inc(&udp_gro_needed);
 }
 EXPORT_SYMBOL_GPL(setup_udp_tunnel_sock);
 
@@ -185,7 +189,12 @@ EXPORT_SYMBOL_GPL(udp_tunnel_xmit_skb);
 
 void udp_tunnel_sock_release(struct socket *sock)
 {
-       rcu_assign_sk_user_data(sock->sk, NULL);
+       struct sock *sk = sock->sk;
+
+       if (udp_sk(sk)->gro_receive)
+               static_branch_dec(&udp_gro_needed);
+
+       rcu_assign_sk_user_data(sk, NULL);
        kernel_sock_shutdown(sock, SHUT_RDWR);
        sock_release(sock);
 }
-- 
2.13.4