tcp: annotate data-races around tp->keepalive_probes

do_tcp_getsockopt() reads tp->keepalive_probes while another cpu
might change its value.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20230719212857.3943972-6-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 2d8d58dec65285f8f0d719d8dc7902b010d1f2d4..a8b93b2875eadedab903328bf56122c13b9643cb 100644 (file)
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1533,9 +1533,14 @@ static inline int keepalive_time_when(const struct tcp_sock *tp)
 static inline int keepalive_probes(const struct tcp_sock *tp)
 {
        struct net *net = sock_net((struct sock *)tp);
+       int val;
+
+       /* Paired with WRITE_ONCE() in tcp_sock_set_keepcnt()
+        * and do_tcp_setsockopt().
+        */
+       val = READ_ONCE(tp->keepalive_probes);
 
-       return tp->keepalive_probes ? :
-               READ_ONCE(net->ipv4.sysctl_tcp_keepalive_probes);
+       return val ? : READ_ONCE(net->ipv4.sysctl_tcp_keepalive_probes);
 }
 
 static inline u32 keepalive_time_elapsed(const struct tcp_sock *tp)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index d55fe014e7c902859243cdb619d94a230e44f708..574fd0da167339512077c36958578fde2b1181e8 100644 (file)
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3357,7 +3357,8 @@ int tcp_sock_set_keepcnt(struct sock *sk, int val)
                return -EINVAL;
 
        lock_sock(sk);
-       tcp_sk(sk)->keepalive_probes = val;
+       /* Paired with READ_ONCE() in keepalive_probes() */
+       WRITE_ONCE(tcp_sk(sk)->keepalive_probes, val);
        release_sock(sk);
        return 0;
 }
@@ -3565,7 +3566,7 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname,
                if (val < 1 || val > MAX_TCP_KEEPCNT)
                        err = -EINVAL;
                else
-                       tp->keepalive_probes = val;
+                       WRITE_ONCE(tp->keepalive_probes, val);
                break;
        case TCP_SYNCNT:
                if (val < 1 || val > MAX_TCP_SYNCNT)