Merge branch 'mptcp-features-and-fixes-for-v6-7'

Mat Martineau says:

====================
mptcp: Features and fixes for v6.7

Patch 1 adds a configurable timeout for the MPTCP connection when all
subflows are closed, to support break-before-make use cases.

Patch 2 is a fix for a 1-byte error in rx data counters with MPTCP
fastopen connections.

Patch 3 is a minor code cleanup.

Patches 4 & 5 add handling of rcvlowat for MPTCP sockets, with a
prerequisite patch to use a common scaling ratio between TCP and MPTCP.

Patch 6 improves efficiency of memory copying in MPTCP transmit code.

Patch 7 refactors syncing of socket options from the MPTCP socket to
its subflows.

Patches 8 & 9 help the MPTCP packet scheduler perform well by changing
the handling of notsent_lowat in subflows and how available buffer space
is calculated for MPTCP-level sends.
====================

Link: https://lore.kernel.org/r/20231023-send-net-next-20231023-2-v1-0-9dc60939d371@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 47 insertions, 18 deletions

diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c
index 59bd5e114392..574e221bb765 100644
--- a/net/mptcp/sockopt.c
+++ b/net/mptcp/sockopt.c
@@ -95,6 +95,7 @@ static void mptcp_sol_socket_sync_intval(struct mptcp_sock *msk, int optname, in
 		case SO_SNDBUFFORCE:
 			ssk->sk_userlocks |= SOCK_SNDBUF_LOCK;
 			WRITE_ONCE(ssk->sk_sndbuf, sk->sk_sndbuf);
+			mptcp_subflow_ctx(ssk)->cached_sndbuf = sk->sk_sndbuf;
 			break;
 		case SO_RCVBUF:
 		case SO_RCVBUFFORCE:
@@ -1415,8 +1416,10 @@ static void sync_socket_options(struct mptcp_sock *msk, struct sock *ssk)
 
 	if (sk->sk_userlocks & tx_rx_locks) {
 		ssk->sk_userlocks |= sk->sk_userlocks & tx_rx_locks;
-		if (sk->sk_userlocks & SOCK_SNDBUF_LOCK)
+		if (sk->sk_userlocks & SOCK_SNDBUF_LOCK) {
 			WRITE_ONCE(ssk->sk_sndbuf, sk->sk_sndbuf);
+			mptcp_subflow_ctx(ssk)->cached_sndbuf = sk->sk_sndbuf;
+		}
 		if (sk->sk_userlocks & SOCK_RCVBUF_LOCK)
 			WRITE_ONCE(ssk->sk_rcvbuf, sk->sk_rcvbuf);
 	}
@@ -1444,37 +1447,63 @@ 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;
 }