netdev - [PATCH net-next 06/24] net/ipv4: Use nested-BH locking for ipv4_tcp

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20231215171020.687342-7-bigeasy@linutronix.de>
Date: Fri, 15 Dec 2023 18:07:25 +0100
From: Sebastian Andrzej Siewior <bigeasy@...utronix.de>
To: linux-kernel@...r.kernel.org,
	netdev@...r.kernel.org
Cc: "David S. Miller" <davem@...emloft.net>,
	Boqun Feng <boqun.feng@...il.com>,
	Daniel Borkmann <daniel@...earbox.net>,
	Eric Dumazet <edumazet@...gle.com>,
	Frederic Weisbecker <frederic@...nel.org>,
	Ingo Molnar <mingo@...hat.com>,
	Jakub Kicinski <kuba@...nel.org>,
	Paolo Abeni <pabeni@...hat.com>,
	Peter Zijlstra <peterz@...radead.org>,
	Thomas Gleixner <tglx@...utronix.de>,
	Waiman Long <longman@...hat.com>,
	Will Deacon <will@...nel.org>,
	Sebastian Andrzej Siewior <bigeasy@...utronix.de>,
	David Ahern <dsahern@...nel.org>
Subject: [PATCH net-next 06/24] 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@...nel.org>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@...utronix.de>
---
 include/net/sock.h  |  5 +++++
 net/ipv4/tcp_ipv4.c | 15 +++++++++++----
 2 files changed, 16 insertions(+), 4 deletions(-)

diff --git a/include/net/sock.h b/include/net/sock.h
index 1d6931caf0c3c..cb407b7ae39f8 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -547,6 +547,11 @@ struct sock {
 	struct hlist_node	sk_bind2_node;
 };
 
+struct sock_bh_locked {
+	struct sock *sock;
+	local_lock_t bh_lock;
+};
+
 enum sk_pacing {
 	SK_PACING_NONE		= 0,
 	SK_PACING_NEEDED	= 1,
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 0c50c5a32b84a..e69dd19f39e02 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -92,7 +92,9 @@ 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)
 {
@@ -878,7 +880,9 @@ 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) ?
@@ -903,6 +907,7 @@ 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
@@ -998,7 +1003,8 @@ 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);
@@ -1013,6 +1019,7 @@ 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();
 }
 
@@ -3604,7 +3611,7 @@ void __init tcp_v4_init(void)
 		 */
 		inet_sk(sk)->pmtudisc = IP_PMTUDISC_DO;
 
-		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");
-- 
2.43.0