Commit 3473020d authored by Jakub Kicinski's avatar Jakub Kicinski
Browse files

Merge branch 'mptcp-rx-path-fixes' 

Matthieu Baerts says:

====================
mptcp: rx path fixes

Here are 3 different fixes, all related to the MPTCP receive buffer:

- Patch 1: fix receive buffer space when recvmsg() blocks after
  receiving some data. For a fix introduced in v6.12, backported to
  v6.1.

- Patch 2: mptcp_cleanup_rbuf() can be called when no data has been
  copied. For 5.11.

- Patch 3: prevent excessive coalescing on receive, which can affect the
  throughput badly. It looks better to wait a bit before backporting
  this one to stable versions, to get more results. For 5.10.
====================

Link: https://patch.msgid.link/20241230-net-mptcp-rbuf-fixes-v1-0-8608af434ceb@kernel.org


Signed-off-by: default avatarJakub Kicinski <kuba@kernel.org>
parents 260466b5 56b824eb

net/mptcp/protocol.c

+12 −11
Original line number Diff line number Diff line
@@ -136,6 +136,7 @@ static bool mptcp_try_coalesce(struct sock *sk, struct sk_buff *to, 
	int delta;



	if (MPTCP_SKB_CB(from)->offset ||

	    ((to->len + from->len) > (sk->sk_rcvbuf >> 3)) ||

	    !skb_try_coalesce(to, from, &fragstolen, &delta))

		return false;
@@ -528,13 +529,13 @@ static void mptcp_send_ack(struct mptcp_sock *msk) 
		mptcp_subflow_send_ack(mptcp_subflow_tcp_sock(subflow));

}



static void mptcp_subflow_cleanup_rbuf(struct sock *ssk)

static void mptcp_subflow_cleanup_rbuf(struct sock *ssk, int copied)

{

	bool slow;



	slow = lock_sock_fast(ssk);

	if (tcp_can_send_ack(ssk))

		tcp_cleanup_rbuf(ssk, 1);

		tcp_cleanup_rbuf(ssk, copied);

	unlock_sock_fast(ssk, slow);

}
@@ -551,7 +552,7 @@ static bool mptcp_subflow_could_cleanup(const struct sock *ssk, bool rx_empty) 
			      (ICSK_ACK_PUSHED2 | ICSK_ACK_PUSHED)));

}



static void mptcp_cleanup_rbuf(struct mptcp_sock *msk)

static void mptcp_cleanup_rbuf(struct mptcp_sock *msk, int copied)

{

	int old_space = READ_ONCE(msk->old_wspace);

	struct mptcp_subflow_context *subflow;
@@ -559,14 +560,14 @@ static void mptcp_cleanup_rbuf(struct mptcp_sock *msk) 
	int space =  __mptcp_space(sk);

	bool cleanup, rx_empty;



	cleanup = (space > 0) && (space >= (old_space << 1));

	rx_empty = !__mptcp_rmem(sk);

	cleanup = (space > 0) && (space >= (old_space << 1)) && copied;

	rx_empty = !__mptcp_rmem(sk) && copied;



	mptcp_for_each_subflow(msk, subflow) {

		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);



		if (cleanup || mptcp_subflow_could_cleanup(ssk, rx_empty))

			mptcp_subflow_cleanup_rbuf(ssk);

			mptcp_subflow_cleanup_rbuf(ssk, copied);

	}

}
@@ -1939,6 +1940,8 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) 
	goto out;

}



static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied);



static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk,

				struct msghdr *msg,

				size_t len, int flags,
@@ -1992,6 +1995,7 @@ static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk, 
			break;

	}



	mptcp_rcv_space_adjust(msk, copied);

	return copied;

}
@@ -2217,9 +2221,6 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, 


		copied += bytes_read;



		/* be sure to advertise window change */

		mptcp_cleanup_rbuf(msk);



		if (skb_queue_empty(&msk->receive_queue) && __mptcp_move_skbs(msk))

			continue;
@@ -2268,7 +2269,7 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, 
		}



		pr_debug("block timeout %ld\n", timeo);

		mptcp_rcv_space_adjust(msk, copied);

		mptcp_cleanup_rbuf(msk, copied);

		err = sk_wait_data(sk, &timeo, NULL);

		if (err < 0) {

			err = copied ? : err;
@@ -2276,7 +2277,7 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, 
		}

	}



	mptcp_rcv_space_adjust(msk, copied);

	mptcp_cleanup_rbuf(msk, copied);



out_err:

	if (cmsg_flags && copied >= 0) {