tcp: annotate data-races around tp->window_clamp

tp->window_clamp can be read locklessly, add READ_ONCE()
and WRITE_ONCE() annotations.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Link: https://lore.kernel.org/r/20240404114231.2195171-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

7 files changed, 29 insertions, 23 deletions

diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 500f665f98cbce..b61d36810fe3fd 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -462,7 +462,8 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 	}
 
 	/* Try to redo what tcp_v4_send_synack did. */
-	req->rsk_window_clamp = tp->window_clamp ? :dst_metric(&rt->dst, RTAX_WINDOW);
+	req->rsk_window_clamp = READ_ONCE(tp->window_clamp) ? :
+				dst_metric(&rt->dst, RTAX_WINDOW);
 	/* limit the window selection if the user enforce a smaller rx buffer */
 	full_space = tcp_full_space(sk);
 	if (sk->sk_userlocks & SOCK_RCVBUF_LOCK &&
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index e767721b3a588b..92ee60492314a1 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1721,7 +1721,7 @@ int tcp_set_rcvlowat(struct sock *sk, int val)
 	space = tcp_space_from_win(sk, val);
 	if (space > sk->sk_rcvbuf) {
 		WRITE_ONCE(sk->sk_rcvbuf, space);
-		tcp_sk(sk)->window_clamp = val;
+		WRITE_ONCE(tcp_sk(sk)->window_clamp, val);
 	}
 	return 0;
 }
@@ -3379,7 +3379,7 @@ int tcp_set_window_clamp(struct sock *sk, int val)
 	if (!val) {
 		if (sk->sk_state != TCP_CLOSE)
 			return -EINVAL;
-		tp->window_clamp = 0;
+		WRITE_ONCE(tp->window_clamp, 0);
 	} else {
 		u32 new_rcv_ssthresh, old_window_clamp = tp->window_clamp;
 		u32 new_window_clamp = val < SOCK_MIN_RCVBUF / 2 ?
@@ -3388,7 +3388,7 @@ int tcp_set_window_clamp(struct sock *sk, int val)
 		if (new_window_clamp == old_window_clamp)
 			return 0;
 
-		tp->window_clamp = new_window_clamp;
+		WRITE_ONCE(tp->window_clamp, new_window_clamp);
 		if (new_window_clamp < old_window_clamp) {
 			/* need to apply the reserved mem provisioning only
 			 * when shrinking the window clamp
@@ -4057,7 +4057,7 @@ int do_tcp_getsockopt(struct sock *sk, int level,
 				      TCP_RTO_MAX / HZ);
 		break;
 	case TCP_WINDOW_CLAMP:
-		val = tp->window_clamp;
+		val = READ_ONCE(tp->window_clamp);
 		break;
 	case TCP_INFO: {
 		struct tcp_info info;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 1b6cd384001202..8d44ab5671eacd 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -563,19 +563,20 @@ static void tcp_init_buffer_space(struct sock *sk)
 	maxwin = tcp_full_space(sk);
 
 	if (tp->window_clamp >= maxwin) {
-		tp->window_clamp = maxwin;
+		WRITE_ONCE(tp->window_clamp, maxwin);
 
 		if (tcp_app_win && maxwin > 4 * tp->advmss)
-			tp->window_clamp = max(maxwin -
-					       (maxwin >> tcp_app_win),
-					       4 * tp->advmss);
+			WRITE_ONCE(tp->window_clamp,
+				   max(maxwin - (maxwin >> tcp_app_win),
+				       4 * tp->advmss));
 	}
 
 	/* Force reservation of one segment. */
 	if (tcp_app_win &&
 	    tp->window_clamp > 2 * tp->advmss &&
 	    tp->window_clamp + tp->advmss > maxwin)
-		tp->window_clamp = max(2 * tp->advmss, maxwin - tp->advmss);
+		WRITE_ONCE(tp->window_clamp,
+			   max(2 * tp->advmss, maxwin - tp->advmss));
 
 	tp->rcv_ssthresh = min(tp->rcv_ssthresh, tp->window_clamp);
 	tp->snd_cwnd_stamp = tcp_jiffies32;
@@ -773,7 +774,8 @@ void tcp_rcv_space_adjust(struct sock *sk)
 			WRITE_ONCE(sk->sk_rcvbuf, rcvbuf);
 
 			/* Make the window clamp follow along.  */
-			tp->window_clamp = tcp_win_from_space(sk, rcvbuf);
+			WRITE_ONCE(tp->window_clamp,
+				   tcp_win_from_space(sk, rcvbuf));
 		}
 	}
 	tp->rcvq_space.space = copied;
@@ -6426,7 +6428,8 @@ consume:
 
 		if (!tp->rx_opt.wscale_ok) {
 			tp->rx_opt.snd_wscale = tp->rx_opt.rcv_wscale = 0;
-			tp->window_clamp = min(tp->window_clamp, 65535U);
+			WRITE_ONCE(tp->window_clamp,
+				   min(tp->window_clamp, 65535U));
 		}
 
 		if (tp->rx_opt.saw_tstamp) {
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index e3167ad965676f..9282fafc0e6109 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -203,16 +203,17 @@ static inline void tcp_event_ack_sent(struct sock *sk, u32 rcv_nxt)
  * This MUST be enforced by all callers.
  */
 void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss,
-			       __u32 *rcv_wnd, __u32 *window_clamp,
+			       __u32 *rcv_wnd, __u32 *__window_clamp,
 			       int wscale_ok, __u8 *rcv_wscale,
 			       __u32 init_rcv_wnd)
 {
 	unsigned int space = (__space < 0 ? 0 : __space);
+	u32 window_clamp = READ_ONCE(*__window_clamp);
 
 	/* If no clamp set the clamp to the max possible scaled window */
-	if (*window_clamp == 0)
-		(*window_clamp) = (U16_MAX << TCP_MAX_WSCALE);
-	space = min(*window_clamp, space);
+	if (window_clamp == 0)
+		window_clamp = (U16_MAX << TCP_MAX_WSCALE);
+	space = min(window_clamp, space);
 
 	/* Quantize space offering to a multiple of mss if possible. */
 	if (space > mss)
@@ -239,12 +240,13 @@ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss,
 		/* Set window scaling on max possible window */
 		space = max_t(u32, space, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]));
 		space = max_t(u32, space, READ_ONCE(sysctl_rmem_max));
-		space = min_t(u32, space, *window_clamp);
+		space = min_t(u32, space, window_clamp);
 		*rcv_wscale = clamp_t(int, ilog2(space) - 15,
 				      0, TCP_MAX_WSCALE);
 	}
 	/* Set the clamp no higher than max representable value */
-	(*window_clamp) = min_t(__u32, U16_MAX << (*rcv_wscale), *window_clamp);
+	WRITE_ONCE(*__window_clamp,
+		   min_t(__u32, U16_MAX << (*rcv_wscale), window_clamp));
 }
 EXPORT_SYMBOL(tcp_select_initial_window);
 
@@ -3855,7 +3857,7 @@ static void tcp_connect_init(struct sock *sk)
 	tcp_ca_dst_init(sk, dst);
 
 	if (!tp->window_clamp)
-		tp->window_clamp = dst_metric(dst, RTAX_WINDOW);
+		WRITE_ONCE(tp->window_clamp, dst_metric(dst, RTAX_WINDOW));
 	tp->advmss = tcp_mss_clamp(tp, dst_metric_advmss(dst));
 
 	tcp_initialize_rcv_mss(sk);
@@ -3863,7 +3865,7 @@ static void tcp_connect_init(struct sock *sk)
 	/* limit the window selection if the user enforce a smaller rx buffer */
 	if (sk->sk_userlocks & SOCK_RCVBUF_LOCK &&
 	    (tp->window_clamp > tcp_full_space(sk) || tp->window_clamp == 0))
-		tp->window_clamp = tcp_full_space(sk);
+		WRITE_ONCE(tp->window_clamp, tcp_full_space(sk));
 
 	rcv_wnd = tcp_rwnd_init_bpf(sk);
 	if (rcv_wnd == 0)
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 6d8286c299c9d1..bfad1e89b6a6bb 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -246,7 +246,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 		}
 	}
 
-	req->rsk_window_clamp = tp->window_clamp ? :dst_metric(dst, RTAX_WINDOW);
+	req->rsk_window_clamp = READ_ONCE(tp->window_clamp) ? :dst_metric(dst, RTAX_WINDOW);
 	/* limit the window selection if the user enforce a smaller rx buffer */
 	full_space = tcp_full_space(sk);
 	if (sk->sk_userlocks & SOCK_RCVBUF_LOCK &&
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 7e74b812e366ae..995b53cd021c84 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -2056,7 +2056,7 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied)
 				ssk = mptcp_subflow_tcp_sock(subflow);
 				slow = lock_sock_fast(ssk);
 				WRITE_ONCE(ssk->sk_rcvbuf, rcvbuf);
-				tcp_sk(ssk)->window_clamp = window_clamp;
+				WRITE_ONCE(tcp_sk(ssk)->window_clamp, window_clamp);
 				tcp_cleanup_rbuf(ssk, 1);
 				unlock_sock_fast(ssk, slow);
 			}
diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c
index 73fdf423de44ee..9d5d42a77bcc35 100644
--- a/net/mptcp/sockopt.c
+++ b/net/mptcp/sockopt.c
@@ -1523,7 +1523,7 @@ int mptcp_set_rcvlowat(struct sock *sk, int val)
 
 		slow = lock_sock_fast(ssk);
 		WRITE_ONCE(ssk->sk_rcvbuf, space);
-		tcp_sk(ssk)->window_clamp = val;
+		WRITE_ONCE(tcp_sk(ssk)->window_clamp, val);
 		unlock_sock_fast(ssk, slow);
 	}
 	return 0;