udp: enable busy polling for all sockets

UDP busy polling is restricted to connected UDP sockets.

This is because sk_busy_loop() only takes care of one NAPI context.

There are cases where it could be extended.

1) Some hosts receive traffic on a single NIC, with one RX queue.

2) Some applications use SO_REUSEPORT and associated BPF filter
   to split the incoming traffic on one UDP socket per RX
queue/thread/cpu

3) Some UDP sockets are used to send/receive traffic for one flow, but
they do not bother with connect()

This patch records the napi_id of first received skb, giving more
reach to busy polling.

Tested:

lpaa23:~# echo 70 >/proc/sys/net/core/busy_read
lpaa24:~# echo 70 >/proc/sys/net/core/busy_read

lpaa23:~# for f in `seq 1 10`; do ./super_netperf 1 -H lpaa24 -t UDP_RR -l 5; done

Before patch :
   27867   28870   37324   41060   41215
   36764   36838   44455   41282   43843
After patch :
   73920   73213   70147   74845   71697
   68315   68028   75219   70082   73707

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

include/net/busy_poll.h

@@ -80,11 +80,6 @@ static inline void skb_mark_napi_id(struct sk_buff *skb,
 	skb->napi_id = napi->napi_id;
 }
 
-/* used in the protocol hanlder to propagate the napi_id to the socket */
-static inline void sk_mark_napi_id(struct sock *sk, struct sk_buff *skb)
-{
-	sk->sk_napi_id = skb->napi_id;
-}
 
 #else /* CONFIG_NET_RX_BUSY_POLL */
 static inline unsigned long net_busy_loop_on(void)
@@ -107,10 +102,6 @@ static inline void skb_mark_napi_id(struct sk_buff *skb,
 {
 }
 
-static inline void sk_mark_napi_id(struct sock *sk, struct sk_buff *skb)
-{
-}
-
 static inline bool busy_loop_timeout(unsigned long end_time)
 {
 	return true;
@@ -122,4 +113,23 @@ static inline bool sk_busy_loop(struct sock *sk, int nonblock)
 }
 
 #endif /* CONFIG_NET_RX_BUSY_POLL */
+
+/* used in the protocol hanlder to propagate the napi_id to the socket */
+static inline void sk_mark_napi_id(struct sock *sk, const struct sk_buff *skb)
+{
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	sk->sk_napi_id = skb->napi_id;
+#endif
+}
+
+/* variant used for unconnected sockets */
+static inline void sk_mark_napi_id_once(struct sock *sk,
+					const struct sk_buff *skb)
+{
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	if (!sk->sk_napi_id)
+		sk->sk_napi_id = skb->napi_id;
+#endif
+}
+
 #endif /* _LINUX_NET_BUSY_POLL_H */

net/ipv4/udp.c

@@ -1569,6 +1569,8 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 		sock_rps_save_rxhash(sk, skb);
 		sk_mark_napi_id(sk, skb);
 		sk_incoming_cpu_update(sk);
+	} else {
+		sk_mark_napi_id_once(sk, skb);
 	}
 
 	rc = __udp_enqueue_schedule_skb(sk, skb);

net/ipv6/udp.c

@@ -519,6 +519,8 @@ static int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 		sock_rps_save_rxhash(sk, skb);
 		sk_mark_napi_id(sk, skb);
 		sk_incoming_cpu_update(sk);
+	} else {
+		sk_mark_napi_id_once(sk, skb);
 	}
 
 	rc = __udp_enqueue_schedule_skb(sk, skb);