tcp: tsq: avoid one atomic in tcp_wfree()

Under high load, tcp_wfree() has an atomic operation trying
to schedule a tasklet over and over.

We can schedule it only if our per cpu list was empty.

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

net/ipv4/tcp_output.c

@@ -880,6 +880,7 @@ void tcp_wfree(struct sk_buff *skb)
 
 	for (oval = READ_ONCE(tp->tsq_flags);; oval = nval) {
 		struct tsq_tasklet *tsq;
+		bool empty;
 
 		if (!(oval & TSQF_THROTTLED) || (oval & TSQF_QUEUED))
 			goto out;
@@ -892,8 +893,10 @@ void tcp_wfree(struct sk_buff *skb)
 		/* queue this socket to tasklet queue */
 		local_irq_save(flags);
 		tsq = this_cpu_ptr(&tsq_tasklet);
+		empty = list_empty(&tsq->head);
 		list_add(&tp->tsq_node, &tsq->head);
-		tasklet_schedule(&tsq->tasklet);
+		if (empty)
+			tasklet_schedule(&tsq->tasklet);
 		local_irq_restore(flags);
 		return;
 	}