Merging upstream version 6.7.7.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

1 files changed, 47 insertions, 21 deletions

diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c
index 116e300823..3536807337 100644
--- a/net/mptcp/sockopt.c
+++ b/net/mptcp/sockopt.c
@@ -89,7 +89,7 @@ static void mptcp_sol_socket_sync_intval(struct mptcp_sock *msk, int optname, in
 			sock_valbool_flag(ssk, SOCK_KEEPOPEN, !!val);
 			break;
 		case SO_PRIORITY:
-			ssk->sk_priority = val;
+			WRITE_ONCE(ssk->sk_priority, val);
 			break;
 		case SO_SNDBUF:
 		case SO_SNDBUFFORCE:
@@ -735,7 +735,7 @@ static int mptcp_setsockopt_v4_set_tos(struct mptcp_sock *msk, int optname,
 
 	lock_sock(sk);
 	sockopt_seq_inc(msk);
-	val = inet_sk(sk)->tos;
+	val = READ_ONCE(inet_sk(sk)->tos);
 	mptcp_for_each_subflow(msk, subflow) {
 		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
 		bool slow;
@@ -919,7 +919,7 @@ void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info)
 			mptcp_pm_get_local_addr_max(msk);
 	}
 
-	if (test_bit(MPTCP_FALLBACK_DONE, &msk->flags))
+	if (__mptcp_check_fallback(msk))
 		flags |= MPTCP_INFO_FLAG_FALLBACK;
 	if (READ_ONCE(msk->can_ack))
 		flags |= MPTCP_INFO_FLAG_REMOTE_KEY_RECEIVED;
@@ -1347,7 +1347,7 @@ static int mptcp_getsockopt_v4(struct mptcp_sock *msk, int optname,
 
 	switch (optname) {
 	case IP_TOS:
-		return mptcp_put_int_option(msk, optval, optlen, inet_sk(sk)->tos);
+		return mptcp_put_int_option(msk, optval, optlen, READ_ONCE(inet_sk(sk)->tos));
 	}
 
 	return -EOPNOTSUPP;
@@ -1450,37 +1450,63 @@ static void sync_socket_options(struct mptcp_sock *msk, struct sock *ssk)
 	inet_assign_bit(FREEBIND, ssk, inet_test_bit(FREEBIND, sk));
 }
 
-static void __mptcp_sockopt_sync(struct mptcp_sock *msk, struct sock *ssk)
-{
-	bool slow = lock_sock_fast(ssk);
-
-	sync_socket_options(msk, ssk);
-
-	unlock_sock_fast(ssk, slow);
-}
-
-void mptcp_sockopt_sync(struct mptcp_sock *msk, struct sock *ssk)
+void mptcp_sockopt_sync_locked(struct mptcp_sock *msk, struct sock *ssk)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
 
 	msk_owned_by_me(msk);
 
+	ssk->sk_rcvlowat = 0;
+
+	/* subflows must ignore any latency-related settings: will not affect
+	 * the user-space - only the msk is relevant - but will foul the
+	 * mptcp scheduler
+	 */
+	tcp_sk(ssk)->notsent_lowat = UINT_MAX;
+
 	if (READ_ONCE(subflow->setsockopt_seq) != msk->setsockopt_seq) {
-		__mptcp_sockopt_sync(msk, ssk);
+		sync_socket_options(msk, ssk);
 
 		subflow->setsockopt_seq = msk->setsockopt_seq;
 	}
 }
 
-void mptcp_sockopt_sync_locked(struct mptcp_sock *msk, struct sock *ssk)
+/* unfortunately this is different enough from the tcp version so
+ * that we can't factor it out
+ */
+int mptcp_set_rcvlowat(struct sock *sk, int val)
 {
-	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
+	struct mptcp_subflow_context *subflow;
+	int space, cap;
 
-	msk_owned_by_me(msk);
+	if (sk->sk_userlocks & SOCK_RCVBUF_LOCK)
+		cap = sk->sk_rcvbuf >> 1;
+	else
+		cap = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]) >> 1;
+	val = min(val, cap);
+	WRITE_ONCE(sk->sk_rcvlowat, val ? : 1);
 
-	if (READ_ONCE(subflow->setsockopt_seq) != msk->setsockopt_seq) {
-		sync_socket_options(msk, ssk);
+	/* Check if we need to signal EPOLLIN right now */
+	if (mptcp_epollin_ready(sk))
+		sk->sk_data_ready(sk);
 
-		subflow->setsockopt_seq = msk->setsockopt_seq;
+	if (sk->sk_userlocks & SOCK_RCVBUF_LOCK)
+		return 0;
+
+	space = __tcp_space_from_win(mptcp_sk(sk)->scaling_ratio, val);
+	if (space <= sk->sk_rcvbuf)
+		return 0;
+
+	/* propagate the rcvbuf changes to all the subflows */
+	WRITE_ONCE(sk->sk_rcvbuf, space);
+	mptcp_for_each_subflow(mptcp_sk(sk), subflow) {
+		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+		bool slow;
+
+		slow = lock_sock_fast(ssk);
+		WRITE_ONCE(ssk->sk_rcvbuf, space);
+		tcp_sk(ssk)->window_clamp = val;
+		unlock_sock_fast(ssk, slow);
 	}
+	return 0;
 }