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 4f97c0e2d5f3455375ceb04bd1644980291f14aa..b1a9e6b1a153311c16b9a597063001c2491ce5e9 100644 (file)
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1887,7 +1887,11 @@ 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);
 }
 
 static inline bool tcp_stream_memory_free(const struct sock *sk)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 98811b5f2451a7081022a60f4900ce18217eac67..bcc2a3490323b6b037219777fc1cc477e6a95c90 100644 (file)
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2810,7 +2810,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
                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;
        default:
@@ -3204,7 +3204,7 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
                val = tcp_time_stamp_raw() + tp->tsoffset;
                break;
        case TCP_NOTSENT_LOWAT:
-               val = tp->notsent_lowat;
+               val = READ_ONCE(tp->notsent_lowat);
                break;
        case TCP_SAVE_SYN:
                val = tp->save_syn;