tcp: tsq: add a shortcut in tcp_small_queue_check()

Always allow the two first skbs in write queue to be sent,
regardless of sk_wmem_alloc/sk_pacing_rate values.

This helps a lot in situations where TX completions are delayed either
because of driver latencies or softirq latencies.

Test is done with no cache line misses.

Signed-off-by: Eric Dumazet <[email protected]>
Signed-off-by: David S. Miller <[email protected]>

Author: edumazet

net/ipv4/tcp_output.c

@@ -2091,6 +2091,15 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb,
 	limit <<= factor;
 
 	if (atomic_read(&sk->sk_wmem_alloc) > limit) {
+		/* Always send the 1st or 2nd skb in write queue.
+		 * No need to wait for TX completion to call us back,
+		 * after softirq/tasklet schedule.
+		 * This helps when TX completions are delayed too much.
+		 */
+		if (skb == sk->sk_write_queue.next ||
+		    skb->prev == sk->sk_write_queue.next)
+			return false;
+
 		set_bit(TSQ_THROTTLED, &tcp_sk(sk)->tsq_flags);
 		/* It is possible TX completion already happened
 		 * before we set TSQ_THROTTLED, so we must