net: annotate sk->sk_rcvlowat lockless reads

sock_rcvlowat() or int_sk_rcvlowat() might be called without the socket
lock for example from tcp_poll().

Use READ_ONCE() to document the fact that other cpus might change
sk->sk_rcvlowat under us and avoid KCSAN splats.

Use WRITE_ONCE() on write sides too.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>

diff --git a/include/net/sock.h b/include/net/sock.h
index 2c53f1a1d905409247b1bdafdfaf99d86e430cd0..79f54e1f88277dc7cc64ca0f35fd5ba869a2f96d 100644 (file)
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2271,7 +2271,9 @@ static inline long sock_sndtimeo(const struct sock *sk, bool noblock)
 
 static inline int sock_rcvlowat(const struct sock *sk, int waitall, int len)
 {
-       return (waitall ? len : min_t(int, sk->sk_rcvlowat, len)) ? : 1;
+       int v = waitall ? len : min_t(int, READ_ONCE(sk->sk_rcvlowat), len);
+
+       return v ?: 1;
 }
 
 /* Alas, with timeout socket operations are not restartable.

diff --git a/net/core/filter.c b/net/core/filter.c
index ed6563622ce31dcced4e6ba622770e26f1f7756a..a50c0b6846f29006268b2fb18303d692533bc081 100644 (file)
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4274,7 +4274,7 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock,
                case SO_RCVLOWAT:
                        if (val < 0)
                                val = INT_MAX;
-                       sk->sk_rcvlowat = val ? : 1;
+                       WRITE_ONCE(sk->sk_rcvlowat, val ? : 1);
                        break;
                case SO_MARK:
                        if (sk->sk_mark != val) {

diff --git a/net/core/sock.c b/net/core/sock.c
index 1cf06934da50b98fccc849d396680cee46badb7d..b7c5c6ea51baf88548e73abd85c8f77cf29a2249 100644 (file)
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -974,7 +974,7 @@ set_rcvbuf:
                if (sock->ops->set_rcvlowat)
                        ret = sock->ops->set_rcvlowat(sk, val);
                else
-                       sk->sk_rcvlowat = val ? : 1;
+                       WRITE_ONCE(sk->sk_rcvlowat, val ? : 1);
                break;
 
        case SO_RCVTIMEO_OLD:

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 888c92b63f5a6dc4b935cca7c979c1e559126d44..8781a92ea4b6e4ee9ceeb763dae01970e7f4438a 100644 (file)
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1699,7 +1699,7 @@ int tcp_set_rcvlowat(struct sock *sk, int val)
        else
                cap = sock_net(sk)->ipv4.sysctl_tcp_rmem[2] >> 1;
        val = min(val, cap);
-       sk->sk_rcvlowat = val ? : 1;
+       WRITE_ONCE(sk->sk_rcvlowat, val ? : 1);
 
        /* Check if we need to signal EPOLLIN right now */
        tcp_data_ready(sk);

diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c
index 82bd14e7ac93dc709483b3437cdc1779b34d0888..4c9122fc35c9d5f86ed60bc03427da1cde57b636 100644 (file)
--- a/net/sched/em_meta.c
+++ b/net/sched/em_meta.c
@@ -554,7 +554,7 @@ META_COLLECTOR(int_sk_rcvlowat)
                *err = -1;
                return;
        }
-       dst->value = sk->sk_rcvlowat;
+       dst->value = READ_ONCE(sk->sk_rcvlowat);
 }
 
 META_COLLECTOR(int_sk_rcvtimeo)