net/ipv4: Use nested-BH locking for ipv4_tcp_sk.

ipv4_tcp_sk is a per-CPU variable and relies on disabled BH for its
locking. Without per-CPU locking in local_bh_disable() on PREEMPT_RT
this data structure requires explicit locking.

Make a struct with a sock member (original ipv4_tcp_sk) and a
local_lock_t and use local_lock_nested_bh() for locking. This change
adds only lockdep coverage and does not alter the functional behaviour
for !PREEMPT_RT.

Cc: David Ahern <dsahern@kernel.org>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Link: https://patch.msgid.link/20240620132727.660738-7-bigeasy@linutronix.deSigned-off-by: Jakub Kicinski <kuba@kernel.org>

include/net/sock.h

@@ -544,6 +544,11 @@ struct sock {
 	netns_tracker		ns_tracker;
 };
 
+struct sock_bh_locked {
+	struct sock *sock;
+	local_lock_t bh_lock;
+};
+
 enum sk_pacing {
 	SK_PACING_NONE		= 0,
 	SK_PACING_NEEDED	= 1,

net/ipv4/tcp_ipv4.c

@@ -93,7 +93,9 @@ static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key,
 struct inet_hashinfo tcp_hashinfo;
 EXPORT_SYMBOL(tcp_hashinfo);
 
-static DEFINE_PER_CPU(struct sock *, ipv4_tcp_sk);
+static DEFINE_PER_CPU(struct sock_bh_locked, ipv4_tcp_sk) = {
+	.bh_lock = INIT_LOCAL_LOCK(bh_lock),
+};
 
 static u32 tcp_v4_init_seq(const struct sk_buff *skb)
 {
@@ -882,7 +884,9 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb,
 	arg.tos = ip_hdr(skb)->tos;
 	arg.uid = sock_net_uid(net, sk && sk_fullsock(sk) ? sk : NULL);
 	local_bh_disable();
-	ctl_sk = this_cpu_read(ipv4_tcp_sk);
+	local_lock_nested_bh(&ipv4_tcp_sk.bh_lock);
+	ctl_sk = this_cpu_read(ipv4_tcp_sk.sock);
+
 	sock_net_set(ctl_sk, net);
 	if (sk) {
 		ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ?
@@ -907,6 +911,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb,
 	sock_net_set(ctl_sk, &init_net);
 	__TCP_INC_STATS(net, TCP_MIB_OUTSEGS);
 	__TCP_INC_STATS(net, TCP_MIB_OUTRSTS);
+	local_unlock_nested_bh(&ipv4_tcp_sk.bh_lock);
 	local_bh_enable();
 
 #ifdef CONFIG_TCP_MD5SIG
@@ -1002,7 +1007,8 @@ static void tcp_v4_send_ack(const struct sock *sk,
 	arg.tos = tos;
 	arg.uid = sock_net_uid(net, sk_fullsock(sk) ? sk : NULL);
 	local_bh_disable();
-	ctl_sk = this_cpu_read(ipv4_tcp_sk);
+	local_lock_nested_bh(&ipv4_tcp_sk.bh_lock);
+	ctl_sk = this_cpu_read(ipv4_tcp_sk.sock);
 	sock_net_set(ctl_sk, net);
 	ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ?
 			   inet_twsk(sk)->tw_mark : READ_ONCE(sk->sk_mark);
@@ -1017,6 +1023,7 @@ static void tcp_v4_send_ack(const struct sock *sk,
 
 	sock_net_set(ctl_sk, &init_net);
 	__TCP_INC_STATS(net, TCP_MIB_OUTSEGS);
+	local_unlock_nested_bh(&ipv4_tcp_sk.bh_lock);
 	local_bh_enable();
 }
 
@@ -3615,7 +3622,7 @@ void __init tcp_v4_init(void)
 
 		sk->sk_clockid = CLOCK_MONOTONIC;
 
-		per_cpu(ipv4_tcp_sk, cpu) = sk;
+		per_cpu(ipv4_tcp_sk.sock, cpu) = sk;
 	}
 	if (register_pernet_subsys(&tcp_sk_ops))
 		panic("Failed to create the TCP control socket.\n");