tcp: annotate data-races around tp->notsent_lowat

[ Upstream commit 1aeb87bc1440c5447a7fa2d6e3c2cca52cbd206b ]

tp->notsent_lowat can be read locklessly from do_tcp_getsockopt()
and tcp_poll().

Fixes: c9bee3b7fdec ("tcp: TCP_NOTSENT_LOWAT socket option")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20230719212857.3943972-10-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 9733d8e4f10af209fbec5666d721b33f2e16c713..e9c8f88f47696229ec1eeec31f6c010dadbd8b13 100644 (file)
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -2059,7 +2059,11 @@ void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr, __be32 daddr);
 static inline u32 tcp_notsent_lowat(const struct tcp_sock *tp)
 {
        struct net *net = sock_net((struct sock *)tp);
-       return tp->notsent_lowat ?: READ_ONCE(net->ipv4.sysctl_tcp_notsent_lowat);
+       u32 val;
+
+       val = READ_ONCE(tp->notsent_lowat);
+
+       return val ?: READ_ONCE(net->ipv4.sysctl_tcp_notsent_lowat);
 }
 
 bool tcp_stream_memory_free(const struct sock *sk, int wake);

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index bc3ad48f923890f2b82aff1657ae5e3308681672..6f3a494b965aee2380c09de7e95a51d4056a9038 100644 (file)
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3770,7 +3770,7 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname,
                err = tcp_repair_set_window(tp, optval, optlen);
                break;
        case TCP_NOTSENT_LOWAT:
-               tp->notsent_lowat = val;
+               WRITE_ONCE(tp->notsent_lowat, val);
                sk->sk_write_space(sk);
                break;
        case TCP_INQ:
@@ -4266,7 +4266,7 @@ int do_tcp_getsockopt(struct sock *sk, int level,
                val = tcp_time_stamp_raw() + READ_ONCE(tp->tsoffset);
                break;
        case TCP_NOTSENT_LOWAT:
-               val = tp->notsent_lowat;
+               val = READ_ONCE(tp->notsent_lowat);
                break;
        case TCP_INQ:
                val = tp->recvmsg_inq;