tcp: tcp_gro_dev_warn() cleanup

Use DO_ONCE_LITE_IF() and __cold attribute to put tcp_gro_dev_warn()
out of line.

This also allows the message to be printed again after a
"echo 1 > /sys/kernel/debug/clear_warn_once"

Also add a READ_ONCE() when reading device mtu, as it could
be changed concurrently.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20231130184135.4130860-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

net/ipv4/tcp_input.c

@@ -202,23 +202,17 @@ static void bpf_skops_established(struct sock *sk, int bpf_op,
 }
 #endif
 
-static void tcp_gro_dev_warn(struct sock *sk, const struct sk_buff *skb,
-			     unsigned int len)
+static __cold void tcp_gro_dev_warn(const struct sock *sk, const struct sk_buff *skb,
+				    unsigned int len)
 {
-	static bool __once __read_mostly;
+	struct net_device *dev;
 
-	if (!__once) {
-		struct net_device *dev;
-
-		__once = true;
-
-		rcu_read_lock();
-		dev = dev_get_by_index_rcu(sock_net(sk), skb->skb_iif);
-		if (!dev || len >= dev->mtu)
-			pr_warn("%s: Driver has suspect GRO implementation, TCP performance may be compromised.\n",
-				dev ? dev->name : "Unknown driver");
-		rcu_read_unlock();
-	}
+	rcu_read_lock();
+	dev = dev_get_by_index_rcu(sock_net(sk), skb->skb_iif);
+	if (!dev || len >= READ_ONCE(dev->mtu))
+		pr_warn("%s: Driver has suspect GRO implementation, TCP performance may be compromised.\n",
+			dev ? dev->name : "Unknown driver");
+	rcu_read_unlock();
 }
 
 /* Adapt the MSS value used to make delayed ack decision to the
@@ -250,9 +244,8 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb)
 		icsk->icsk_ack.rcv_mss = min_t(unsigned int, len,
 					       tcp_sk(sk)->advmss);
 		/* Account for possibly-removed options */
-		if (unlikely(len > icsk->icsk_ack.rcv_mss +
-				   MAX_TCP_OPTION_SPACE))
-			tcp_gro_dev_warn(sk, skb, len);
+		DO_ONCE_LITE_IF(len > icsk->icsk_ack.rcv_mss + MAX_TCP_OPTION_SPACE,
+				tcp_gro_dev_warn, sk, skb, len);
 		/* If the skb has a len of exactly 1*MSS and has the PSH bit
 		 * set then it is likely the end of an application write. So
 		 * more data may not be arriving soon, and yet the data sender