diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 0db63ef..d5c4674 100644
--- a/net/ipv4/tcp_output.c
+++ b/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