From: Eric Dumazet <edumazet@google.com>
Date: Thu, 5 Oct 2023 11:45:04 +0000 (+0000)
Subject: net: sock_dequeue_err_skb() optimization
X-Git-Tag: v6.7-rc1~160^2~206
X-Git-Url: https://repo.jachan.dev/linux.git/commitdiff_plain/48533eca606efcf63ef4080ded5618e0b17ee3d7

net: sock_dequeue_err_skb() optimization

Exit early if the list is empty.

Some applications using TCP zerocopy are calling
recvmsg( ... MSG_ERRQUEUE) and hit this case quite often,
probably because busy polling only deals with sk_receive_queue.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20231005114504.642589-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index da3f96bdd6f6..0401f40973a5 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -5162,6 +5162,9 @@ struct sk_buff *sock_dequeue_err_skb(struct sock *sk)
 	bool icmp_next = false;
 	unsigned long flags;
 
+	if (skb_queue_empty_lockless(q))
+		return NULL;
+
 	spin_lock_irqsave(&q->lock, flags);
 	skb = __skb_dequeue(q);
 	if (skb && (skb_next = skb_peek(q))) {