From 63561a403c7c89d59205401db14fb444c6535cef Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Mon, 14 Sep 2020 10:01:07 +0200
Subject: [PATCH 01/13] mptcp: rethink 'is writable' conditional

Currently, when checking for the 'msk is writable' condition, we
look at the individual subflows write space.
That works well while we send data via a single subflow, but will
not as soon as we will enable concurrent xmit on multiple subflows.

With this change msk becomes writable when the following conditions
hold:
- the socket has some free write space
- there is at least a subflow with write free space

Additionally we need to set the NOSPACE bit on all subflows
before blocking.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mptcp/protocol.c | 71 ++++++++++++++++++++++++++++----------------
 net/mptcp/subflow.c  |  6 ++--
 2 files changed, 50 insertions(+), 27 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 683196225f91..854a8b3b9ecd 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -472,7 +472,7 @@ void mptcp_data_acked(struct sock *sk)
 {
 	mptcp_reset_timer(sk);
 
-	if ((!sk_stream_is_writeable(sk) ||
+	if ((!test_bit(MPTCP_SEND_SPACE, &mptcp_sk(sk)->flags) ||
 	     (inet_sk_state_load(sk) != TCP_ESTABLISHED)) &&
 	    schedule_work(&mptcp_sk(sk)->work))
 		sock_hold(sk);
@@ -567,6 +567,20 @@ static void dfrag_clear(struct sock *sk, struct mptcp_data_frag *dfrag)
 	put_page(dfrag->page);
 }
 
+static bool mptcp_is_writeable(struct mptcp_sock *msk)
+{
+	struct mptcp_subflow_context *subflow;
+
+	if (!sk_stream_is_writeable((struct sock *)msk))
+		return false;
+
+	mptcp_for_each_subflow(msk, subflow) {
+		if (sk_stream_is_writeable(subflow->tcp_sock))
+			return true;
+	}
+	return false;
+}
+
 static void mptcp_clean_una(struct sock *sk)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
@@ -609,8 +623,15 @@ out:
 		sk_mem_reclaim_partial(sk);
 
 		/* Only wake up writers if a subflow is ready */
-		if (test_bit(MPTCP_SEND_SPACE, &msk->flags))
+		if (mptcp_is_writeable(msk)) {
+			set_bit(MPTCP_SEND_SPACE, &mptcp_sk(sk)->flags);
+			smp_mb__after_atomic();
+
+			/* set SEND_SPACE before sk_stream_write_space clears
+			 * NOSPACE
+			 */
 			sk_stream_write_space(sk);
+		}
 	}
 }
 
@@ -801,21 +822,31 @@ out:
 	return ret;
 }
 
-static void mptcp_nospace(struct mptcp_sock *msk, struct socket *sock)
+static void mptcp_nospace(struct mptcp_sock *msk)
 {
+	struct mptcp_subflow_context *subflow;
+
 	clear_bit(MPTCP_SEND_SPACE, &msk->flags);
 	smp_mb__after_atomic(); /* msk->flags is changed by write_space cb */
 
-	/* enables sk->write_space() callbacks */
-	set_bit(SOCK_NOSPACE, &sock->flags);
+	mptcp_for_each_subflow(msk, subflow) {
+		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+		struct socket *sock = READ_ONCE(ssk->sk_socket);
+
+		/* enables ssk->write_space() callbacks */
+		if (sock)
+			set_bit(SOCK_NOSPACE, &sock->flags);
+	}
 }
 
 static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)
 {
 	struct mptcp_subflow_context *subflow;
+	struct sock *sk = (struct sock *)msk;
 	struct sock *backup = NULL;
+	bool free;
 
-	sock_owned_by_me((const struct sock *)msk);
+	sock_owned_by_me(sk);
 
 	if (!mptcp_ext_cache_refill(msk))
 		return NULL;
@@ -823,12 +854,9 @@ static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)
 	mptcp_for_each_subflow(msk, subflow) {
 		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
 
-		if (!sk_stream_memory_free(ssk)) {
-			struct socket *sock = ssk->sk_socket;
-
-			if (sock)
-				mptcp_nospace(msk, sock);
-
+		free = sk_stream_is_writeable(subflow->tcp_sock);
+		if (!free) {
+			mptcp_nospace(msk);
 			return NULL;
 		}
 
@@ -845,16 +873,10 @@ static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)
 	return backup;
 }
 
-static void ssk_check_wmem(struct mptcp_sock *msk, struct sock *ssk)
+static void ssk_check_wmem(struct mptcp_sock *msk)
 {
-	struct socket *sock;
-
-	if (likely(sk_stream_is_writeable(ssk)))
-		return;
-
-	sock = READ_ONCE(ssk->sk_socket);
-	if (sock)
-		mptcp_nospace(msk, sock);
+	if (unlikely(!mptcp_is_writeable(msk)))
+		mptcp_nospace(msk);
 }
 
 static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
@@ -907,6 +929,7 @@ restart:
 				mptcp_reset_timer(sk);
 		}
 
+		mptcp_nospace(msk);
 		ret = sk_stream_wait_memory(sk, &timeo);
 		if (ret)
 			goto out;
@@ -945,7 +968,6 @@ restart:
 		if (!sk_stream_memory_free(ssk) ||
 		    !mptcp_page_frag_refill(ssk, pfrag) ||
 		    !mptcp_ext_cache_refill(msk)) {
-			set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
 			tcp_push(ssk, msg->msg_flags, mss_now,
 				 tcp_sk(ssk)->nonagle, size_goal);
 			mptcp_set_timeout(sk, ssk);
@@ -993,9 +1015,9 @@ restart:
 			mptcp_reset_timer(sk);
 	}
 
-	ssk_check_wmem(msk, ssk);
 	release_sock(ssk);
 out:
+	ssk_check_wmem(msk);
 	release_sock(sk);
 	return copied ? : ret;
 }
@@ -2291,8 +2313,7 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock,
 
 	if (state != TCP_SYN_SENT && state != TCP_SYN_RECV) {
 		mask |= mptcp_check_readable(msk);
-		if (sk_stream_is_writeable(sk) &&
-		    test_bit(MPTCP_SEND_SPACE, &msk->flags))
+		if (test_bit(MPTCP_SEND_SPACE, &msk->flags))
 			mask |= EPOLLOUT | EPOLLWRNORM;
 	}
 	if (sk->sk_shutdown & RCV_SHUTDOWN)
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index e8cac2655c82..7ae1d3604047 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -996,8 +996,10 @@ static void subflow_write_space(struct sock *sk)
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
 	struct sock *parent = subflow->conn;
 
-	sk_stream_write_space(sk);
-	if (sk_stream_is_writeable(sk)) {
+	if (!sk_stream_is_writeable(sk))
+		return;
+
+	if (sk_stream_is_writeable(parent)) {
 		set_bit(MPTCP_SEND_SPACE, &mptcp_sk(parent)->flags);
 		smp_mb__after_atomic();
 		/* set SEND_SPACE before sk_stream_write_space clears NOSPACE */

From 47bebdf365ade17534f6616dc228d347085f4501 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Mon, 14 Sep 2020 10:01:08 +0200
Subject: [PATCH 02/13] mptcp: set data_ready status bit in
 subflow_check_data_avail()

This simplify mptcp_subflow_data_available() and will
made follow-up patches simpler.

Additionally remove the unneeded checks on subflow copied_seq:
we always whole skbs out of subflows.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mptcp/subflow.c | 19 ++++++++-----------
 1 file changed, 8 insertions(+), 11 deletions(-)

diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 7ae1d3604047..53b455c3c229 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -825,6 +825,8 @@ static bool subflow_check_data_avail(struct sock *ssk)
 
 	pr_debug("msk=%p ssk=%p data_avail=%d skb=%p", subflow->conn, ssk,
 		 subflow->data_avail, skb_peek(&ssk->sk_receive_queue));
+	if (!skb_peek(&ssk->sk_receive_queue))
+		subflow->data_avail = 0;
 	if (subflow->data_avail)
 		return true;
 
@@ -849,6 +851,7 @@ static bool subflow_check_data_avail(struct sock *ssk)
 			subflow->map_data_len = skb->len;
 			subflow->map_subflow_seq = tcp_sk(ssk)->copied_seq -
 						   subflow->ssn_offset;
+			subflow->data_avail = 1;
 			return true;
 		}
 
@@ -876,8 +879,10 @@ static bool subflow_check_data_avail(struct sock *ssk)
 		ack_seq = mptcp_subflow_get_mapped_dsn(subflow);
 		pr_debug("msk ack_seq=%llx subflow ack_seq=%llx", old_ack,
 			 ack_seq);
-		if (ack_seq == old_ack)
+		if (ack_seq == old_ack) {
+			subflow->data_avail = 1;
 			break;
+		}
 
 		/* only accept in-sequence mapping. Old values are spurious
 		 * retransmission; we can hit "future" values on active backup
@@ -922,13 +927,13 @@ fatal:
 	ssk->sk_error_report(ssk);
 	tcp_set_state(ssk, TCP_CLOSE);
 	tcp_send_active_reset(ssk, GFP_ATOMIC);
+	subflow->data_avail = 0;
 	return false;
 }
 
 bool mptcp_subflow_data_available(struct sock *sk)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
-	struct sk_buff *skb;
 
 	/* check if current mapping is still valid */
 	if (subflow->map_valid &&
@@ -941,15 +946,7 @@ bool mptcp_subflow_data_available(struct sock *sk)
 			 subflow->map_data_len);
 	}
 
-	if (!subflow_check_data_avail(sk)) {
-		subflow->data_avail = 0;
-		return false;
-	}
-
-	skb = skb_peek(&sk->sk_receive_queue);
-	subflow->data_avail = skb &&
-		       before(tcp_sk(sk)->copied_seq, TCP_SKB_CB(skb)->end_seq);
-	return subflow->data_avail;
+	return subflow_check_data_avail(sk);
 }
 
 /* If ssk has an mptcp parent socket, use the mptcp rcvbuf occupancy,

From 6719331c2f736fba881f2ce85c8b0e37fe054c46 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Mon, 14 Sep 2020 10:01:09 +0200
Subject: [PATCH 03/13] mptcp: trigger msk processing even for OoO data

This is a prerequisite to allow receiving data from multiple
subflows without re-injection.

Instead of dropping the OoO - "future" data in
subflow_check_data_avail(), call into __mptcp_move_skbs()
and let the msk drop that.

To avoid code duplication factor out the mptcp_subflow_discard_data()
helper.

Note that __mptcp_move_skbs() can now find multiple subflows
with data avail (comprising to-be-discarded data), so must
update the byte counter incrementally.

v1 -> v2:
 - fix checkpatch issues (unsigned -> unsigned int)

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mptcp/protocol.c | 33 +++++++++++++++----
 net/mptcp/protocol.h |  9 ++++-
 net/mptcp/subflow.c  | 78 ++++++++++++++++++++++++--------------------
 3 files changed, 78 insertions(+), 42 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 854a8b3b9ecd..95573c6f7762 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -167,7 +167,8 @@ static bool mptcp_subflow_dsn_valid(const struct mptcp_sock *msk,
 		return true;
 
 	subflow->data_avail = 0;
-	return mptcp_subflow_data_available(ssk);
+	mptcp_subflow_data_available(ssk);
+	return subflow->data_avail == MPTCP_SUBFLOW_DATA_AVAIL;
 }
 
 static void mptcp_check_data_fin_ack(struct sock *sk)
@@ -313,11 +314,18 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk,
 	struct tcp_sock *tp;
 	bool done = false;
 
-	if (!mptcp_subflow_dsn_valid(msk, ssk)) {
-		*bytes = 0;
+	pr_debug("msk=%p ssk=%p data avail=%d valid=%d empty=%d",
+		 msk, ssk, subflow->data_avail,
+		 mptcp_subflow_dsn_valid(msk, ssk),
+		 !skb_peek(&ssk->sk_receive_queue));
+	if (subflow->data_avail == MPTCP_SUBFLOW_OOO_DATA) {
+		mptcp_subflow_discard_data(ssk, subflow->map_data_len);
 		return false;
 	}
 
+	if (!mptcp_subflow_dsn_valid(msk, ssk))
+		return false;
+
 	tp = tcp_sk(ssk);
 	do {
 		u32 map_remaining, offset;
@@ -376,7 +384,7 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk,
 		}
 	} while (more_data_avail);
 
-	*bytes = moved;
+	*bytes += moved;
 
 	/* If the moves have caught up with the DATA_FIN sequence number
 	 * it's time to ack the DATA_FIN and change socket state, but
@@ -415,9 +423,17 @@ static bool move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk)
 
 void mptcp_data_ready(struct sock *sk, struct sock *ssk)
 {
+	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
 	struct mptcp_sock *msk = mptcp_sk(sk);
+	bool wake;
 
-	set_bit(MPTCP_DATA_READY, &msk->flags);
+	/* move_skbs_to_msk below can legitly clear the data_avail flag,
+	 * but we will need later to properly woke the reader, cache its
+	 * value
+	 */
+	wake = subflow->data_avail == MPTCP_SUBFLOW_DATA_AVAIL;
+	if (wake)
+		set_bit(MPTCP_DATA_READY, &msk->flags);
 
 	if (atomic_read(&sk->sk_rmem_alloc) < READ_ONCE(sk->sk_rcvbuf) &&
 	    move_skbs_to_msk(msk, ssk))
@@ -438,7 +454,8 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk)
 		move_skbs_to_msk(msk, ssk);
 	}
 wake:
-	sk->sk_data_ready(sk);
+	if (wake)
+		sk->sk_data_ready(sk);
 }
 
 static void __mptcp_flush_join_list(struct mptcp_sock *msk)
@@ -1281,6 +1298,9 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		set_bit(MPTCP_DATA_READY, &msk->flags);
 	}
 out_err:
+	pr_debug("msk=%p data_ready=%d rx queue empty=%d copied=%d",
+		 msk, test_bit(MPTCP_DATA_READY, &msk->flags),
+		 skb_queue_empty(&sk->sk_receive_queue), copied);
 	mptcp_rcv_space_adjust(msk, copied);
 
 	release_sock(sk);
@@ -2308,6 +2328,7 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock,
 	sock_poll_wait(file, sock, wait);
 
 	state = inet_sk_state_load(sk);
+	pr_debug("msk=%p state=%d flags=%lx", msk, state, msk->flags);
 	if (state == TCP_LISTEN)
 		return mptcp_check_readable(msk);
 
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 60b27d44c184..794997852c5e 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -268,6 +268,12 @@ mptcp_subflow_rsk(const struct request_sock *rsk)
 	return (struct mptcp_subflow_request_sock *)rsk;
 }
 
+enum mptcp_data_avail {
+	MPTCP_SUBFLOW_NODATA,
+	MPTCP_SUBFLOW_DATA_AVAIL,
+	MPTCP_SUBFLOW_OOO_DATA
+};
+
 /* MPTCP subflow context */
 struct mptcp_subflow_context {
 	struct	list_head node;/* conn_list of subflows */
@@ -292,10 +298,10 @@ struct mptcp_subflow_context {
 		map_valid : 1,
 		mpc_map : 1,
 		backup : 1,
-		data_avail : 1,
 		rx_eof : 1,
 		use_64bit_ack : 1, /* Set when we received a 64-bit DSN */
 		can_ack : 1;	    /* only after processing the remote a key */
+	enum mptcp_data_avail data_avail;
 	u32	remote_nonce;
 	u64	thmac;
 	u32	local_nonce;
@@ -347,6 +353,7 @@ int mptcp_is_enabled(struct net *net);
 void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow,
 				     struct mptcp_options_received *mp_opt);
 bool mptcp_subflow_data_available(struct sock *sk);
+int mptcp_subflow_discard_data(struct sock *sk, unsigned int limit);
 void __init mptcp_subflow_init(void);
 
 /* called with sk socket lock held */
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 53b455c3c229..071ee54b3c9f 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -816,6 +816,40 @@ static int subflow_read_actor(read_descriptor_t *desc,
 	return copy_len;
 }
 
+int mptcp_subflow_discard_data(struct sock *ssk, unsigned int limit)
+{
+	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
+	u32 map_remaining;
+	size_t delta;
+
+	map_remaining = subflow->map_data_len -
+			mptcp_subflow_get_map_offset(subflow);
+	delta = min_t(size_t, limit, map_remaining);
+
+	/* discard mapped data */
+	pr_debug("discarding %zu bytes, current map len=%d", delta,
+		 map_remaining);
+	if (delta) {
+		read_descriptor_t desc = {
+			.count = delta,
+		};
+		int ret;
+
+		ret = tcp_read_sock(ssk, &desc, subflow_read_actor);
+		if (ret < 0) {
+			ssk->sk_err = -ret;
+			return ret;
+		}
+		if (ret < delta)
+			return 0;
+		if (delta == map_remaining) {
+			subflow->data_avail = 0;
+			subflow->map_valid = 0;
+		}
+	}
+	return 0;
+}
+
 static bool subflow_check_data_avail(struct sock *ssk)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
@@ -832,8 +866,6 @@ static bool subflow_check_data_avail(struct sock *ssk)
 
 	msk = mptcp_sk(subflow->conn);
 	for (;;) {
-		u32 map_remaining;
-		size_t delta;
 		u64 ack_seq;
 		u64 old_ack;
 
@@ -851,7 +883,7 @@ static bool subflow_check_data_avail(struct sock *ssk)
 			subflow->map_data_len = skb->len;
 			subflow->map_subflow_seq = tcp_sk(ssk)->copied_seq -
 						   subflow->ssn_offset;
-			subflow->data_avail = 1;
+			subflow->data_avail = MPTCP_SUBFLOW_DATA_AVAIL;
 			return true;
 		}
 
@@ -880,43 +912,19 @@ static bool subflow_check_data_avail(struct sock *ssk)
 		pr_debug("msk ack_seq=%llx subflow ack_seq=%llx", old_ack,
 			 ack_seq);
 		if (ack_seq == old_ack) {
-			subflow->data_avail = 1;
+			subflow->data_avail = MPTCP_SUBFLOW_DATA_AVAIL;
+			break;
+		} else if (after64(ack_seq, old_ack)) {
+			subflow->data_avail = MPTCP_SUBFLOW_OOO_DATA;
 			break;
 		}
 
 		/* only accept in-sequence mapping. Old values are spurious
-		 * retransmission; we can hit "future" values on active backup
-		 * subflow switch, we relay on retransmissions to get
-		 * in-sequence data.
-		 * Cuncurrent subflows support will require subflow data
-		 * reordering
+		 * retransmission
 		 */
-		map_remaining = subflow->map_data_len -
-				mptcp_subflow_get_map_offset(subflow);
-		if (before64(ack_seq, old_ack))
-			delta = min_t(size_t, old_ack - ack_seq, map_remaining);
-		else
-			delta = min_t(size_t, ack_seq - old_ack, map_remaining);
-
-		/* discard mapped data */
-		pr_debug("discarding %zu bytes, current map len=%d", delta,
-			 map_remaining);
-		if (delta) {
-			read_descriptor_t desc = {
-				.count = delta,
-			};
-			int ret;
-
-			ret = tcp_read_sock(ssk, &desc, subflow_read_actor);
-			if (ret < 0) {
-				ssk->sk_err = -ret;
-				goto fatal;
-			}
-			if (ret < delta)
-				return false;
-			if (delta == map_remaining)
-				subflow->map_valid = 0;
-		}
+		if (mptcp_subflow_discard_data(ssk, old_ack - ack_seq))
+			goto fatal;
+		return false;
 	}
 	return true;
 

From da51aef5fe5b9ef389055f693472d4fb5a3f58f9 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Mon, 14 Sep 2020 10:01:10 +0200
Subject: [PATCH 04/13] mptcp: basic sndbuf autotuning

Let the msk sendbuf track the size of the larger subflow's
send window, so that we ensure mptcp_sendmsg() does not
exceed MPTCP-level send window.

The update is performed just before try to send any data.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mptcp/protocol.c | 17 +++++++++++++----
 1 file changed, 13 insertions(+), 4 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 95573c6f7762..4f12a8ce0ddd 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -856,7 +856,8 @@ static void mptcp_nospace(struct mptcp_sock *msk)
 	}
 }
 
-static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)
+static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk,
+					   u32 *sndbuf)
 {
 	struct mptcp_subflow_context *subflow;
 	struct sock *sk = (struct sock *)msk;
@@ -865,6 +866,7 @@ static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)
 
 	sock_owned_by_me(sk);
 
+	*sndbuf = 0;
 	if (!mptcp_ext_cache_refill(msk))
 		return NULL;
 
@@ -877,6 +879,7 @@ static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)
 			return NULL;
 		}
 
+		*sndbuf = max(tcp_sk(ssk)->snd_wnd, *sndbuf);
 		if (subflow->backup) {
 			if (!backup)
 				backup = ssk;
@@ -903,6 +906,7 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	struct page_frag *pfrag;
 	size_t copied = 0;
 	struct sock *ssk;
+	u32 sndbuf;
 	bool tx_ok;
 	long timeo;
 
@@ -929,7 +933,7 @@ restart:
 	}
 
 	__mptcp_flush_join_list(msk);
-	ssk = mptcp_subflow_get_send(msk);
+	ssk = mptcp_subflow_get_send(msk, &sndbuf);
 	while (!sk_stream_memory_free(sk) ||
 	       !ssk ||
 	       !mptcp_page_frag_refill(ssk, pfrag)) {
@@ -953,13 +957,18 @@ restart:
 
 		mptcp_clean_una(sk);
 
-		ssk = mptcp_subflow_get_send(msk);
+		ssk = mptcp_subflow_get_send(msk, &sndbuf);
 		if (list_empty(&msk->conn_list)) {
 			ret = -ENOTCONN;
 			goto out;
 		}
 	}
 
+	/* do auto tuning */
+	if (!(sk->sk_userlocks & SOCK_SNDBUF_LOCK) &&
+	    sndbuf > READ_ONCE(sk->sk_sndbuf))
+		WRITE_ONCE(sk->sk_sndbuf, sndbuf);
+
 	pr_debug("conn_list->subflow=%p", ssk);
 
 	lock_sock(ssk);
@@ -1547,7 +1556,7 @@ static int mptcp_init_sock(struct sock *sk)
 
 	sk_sockets_allocated_inc(sk);
 	sk->sk_rcvbuf = sock_net(sk)->ipv4.sysctl_tcp_rmem[1];
-	sk->sk_sndbuf = sock_net(sk)->ipv4.sysctl_tcp_wmem[2];
+	sk->sk_sndbuf = sock_net(sk)->ipv4.sysctl_tcp_wmem[1];
 
 	return 0;
 }

From 8268ed4c9d197fc6448b6262c62aad62ef9aa4d5 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Mon, 14 Sep 2020 10:01:11 +0200
Subject: [PATCH 05/13] mptcp: introduce and use mptcp_try_coalesce()

Factor-out existing code, will be re-used by the
next patch.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mptcp/protocol.c | 31 +++++++++++++++++++------------
 1 file changed, 19 insertions(+), 12 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 4f12a8ce0ddd..5a2ff333e426 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -110,6 +110,22 @@ static int __mptcp_socket_create(struct mptcp_sock *msk)
 	return 0;
 }
 
+static bool mptcp_try_coalesce(struct sock *sk, struct sk_buff *to,
+			       struct sk_buff *from)
+{
+	bool fragstolen;
+	int delta;
+
+	if (MPTCP_SKB_CB(from)->offset ||
+	    !skb_try_coalesce(to, from, &fragstolen, &delta))
+		return false;
+
+	kfree_skb_partial(from, fragstolen);
+	atomic_add(delta, &sk->sk_rmem_alloc);
+	sk_mem_charge(sk, delta);
+	return true;
+}
+
 static void __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk,
 			     struct sk_buff *skb,
 			     unsigned int offset, size_t copy_len)
@@ -121,24 +137,15 @@ static void __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk,
 
 	skb_ext_reset(skb);
 	skb_orphan(skb);
+	MPTCP_SKB_CB(skb)->offset = offset;
 	msk->ack_seq += copy_len;
 
 	tail = skb_peek_tail(&sk->sk_receive_queue);
-	if (offset == 0 && tail) {
-		bool fragstolen;
-		int delta;
-
-		if (skb_try_coalesce(tail, skb, &fragstolen, &delta)) {
-			kfree_skb_partial(skb, fragstolen);
-			atomic_add(delta, &sk->sk_rmem_alloc);
-			sk_mem_charge(sk, delta);
-			return;
-		}
-	}
+	if (tail && mptcp_try_coalesce(sk, tail, skb))
+		return;
 
 	skb_set_owner_r(skb, sk);
 	__skb_queue_tail(&sk->sk_receive_queue, skb);
-	MPTCP_SKB_CB(skb)->offset = offset;
 }
 
 static void mptcp_stop_timer(struct sock *sk)

From ab174ad8ef76276cadfdae98731d31797d265927 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Mon, 14 Sep 2020 10:01:12 +0200
Subject: [PATCH 06/13] mptcp: move ooo skbs into msk out of order queue.

Add an RB-tree to cope with OoO (at MPTCP level) data.
__mptcp_move_skb() insert into the RB tree "future"
data, eventually coalescing skb as allowed by the
MPTCP DSN.

To simplify sequence accounting, move the DSN inside
the cb.

After successfully enqueuing in sequence data, check
if we can use any data from the RB tree.

Additionally move the data_fin check after spooling
data from the OoO tree, otherwise we could miss shutdown
events.

The RB tree code is copied as verbatim as possible
from tcp_data_queue_ofo(), with a few simplifications
due to the fact that MPTCP doesn't need to cope with
sacks. All bugs here are added by me.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mptcp/protocol.c | 264 ++++++++++++++++++++++++++++++++++---------
 net/mptcp/protocol.h |   2 +
 net/mptcp/subflow.c  |   1 +
 3 files changed, 211 insertions(+), 56 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 5a2ff333e426..6fbfbab51660 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -32,6 +32,8 @@ struct mptcp6_sock {
 #endif
 
 struct mptcp_skb_cb {
+	u64 map_seq;
+	u64 end_seq;
 	u32 offset;
 };
 
@@ -110,6 +112,12 @@ static int __mptcp_socket_create(struct mptcp_sock *msk)
 	return 0;
 }
 
+static void mptcp_drop(struct sock *sk, struct sk_buff *skb)
+{
+	sk_drops_add(sk, skb);
+	__kfree_skb(skb);
+}
+
 static bool mptcp_try_coalesce(struct sock *sk, struct sk_buff *to,
 			       struct sk_buff *from)
 {
@@ -120,16 +128,127 @@ static bool mptcp_try_coalesce(struct sock *sk, struct sk_buff *to,
 	    !skb_try_coalesce(to, from, &fragstolen, &delta))
 		return false;
 
+	MPTCP_SKB_CB(to)->end_seq = MPTCP_SKB_CB(from)->end_seq;
 	kfree_skb_partial(from, fragstolen);
 	atomic_add(delta, &sk->sk_rmem_alloc);
 	sk_mem_charge(sk, delta);
 	return true;
 }
 
-static void __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk,
-			     struct sk_buff *skb,
-			     unsigned int offset, size_t copy_len)
+static bool mptcp_ooo_try_coalesce(struct mptcp_sock *msk, struct sk_buff *to,
+				   struct sk_buff *from)
 {
+	if (MPTCP_SKB_CB(from)->map_seq != MPTCP_SKB_CB(to)->end_seq)
+		return false;
+
+	return mptcp_try_coalesce((struct sock *)msk, to, from);
+}
+
+/* "inspired" by tcp_data_queue_ofo(), main differences:
+ * - use mptcp seqs
+ * - don't cope with sacks
+ */
+static void mptcp_data_queue_ofo(struct mptcp_sock *msk, struct sk_buff *skb)
+{
+	struct sock *sk = (struct sock *)msk;
+	struct rb_node **p, *parent;
+	u64 seq, end_seq, max_seq;
+	struct sk_buff *skb1;
+
+	seq = MPTCP_SKB_CB(skb)->map_seq;
+	end_seq = MPTCP_SKB_CB(skb)->end_seq;
+	max_seq = tcp_space(sk);
+	max_seq = max_seq > 0 ? max_seq + msk->ack_seq : msk->ack_seq;
+
+	if (after64(seq, max_seq)) {
+		/* out of window */
+		mptcp_drop(sk, skb);
+		return;
+	}
+
+	p = &msk->out_of_order_queue.rb_node;
+	if (RB_EMPTY_ROOT(&msk->out_of_order_queue)) {
+		rb_link_node(&skb->rbnode, NULL, p);
+		rb_insert_color(&skb->rbnode, &msk->out_of_order_queue);
+		msk->ooo_last_skb = skb;
+		goto end;
+	}
+
+	/* with 2 subflows, adding at end of ooo queue is quite likely
+	 * Use of ooo_last_skb avoids the O(Log(N)) rbtree lookup.
+	 */
+	if (mptcp_ooo_try_coalesce(msk, msk->ooo_last_skb, skb))
+		return;
+
+	/* Can avoid an rbtree lookup if we are adding skb after ooo_last_skb */
+	if (!before64(seq, MPTCP_SKB_CB(msk->ooo_last_skb)->end_seq)) {
+		parent = &msk->ooo_last_skb->rbnode;
+		p = &parent->rb_right;
+		goto insert;
+	}
+
+	/* Find place to insert this segment. Handle overlaps on the way. */
+	parent = NULL;
+	while (*p) {
+		parent = *p;
+		skb1 = rb_to_skb(parent);
+		if (before64(seq, MPTCP_SKB_CB(skb1)->map_seq)) {
+			p = &parent->rb_left;
+			continue;
+		}
+		if (before64(seq, MPTCP_SKB_CB(skb1)->end_seq)) {
+			if (!after64(end_seq, MPTCP_SKB_CB(skb1)->end_seq)) {
+				/* All the bits are present. Drop. */
+				mptcp_drop(sk, skb);
+				return;
+			}
+			if (after64(seq, MPTCP_SKB_CB(skb1)->map_seq)) {
+				/* partial overlap:
+				 *     |     skb      |
+				 *  |     skb1    |
+				 * continue traversing
+				 */
+			} else {
+				/* skb's seq == skb1's seq and skb covers skb1.
+				 * Replace skb1 with skb.
+				 */
+				rb_replace_node(&skb1->rbnode, &skb->rbnode,
+						&msk->out_of_order_queue);
+				mptcp_drop(sk, skb1);
+				goto merge_right;
+			}
+		} else if (mptcp_ooo_try_coalesce(msk, skb1, skb)) {
+			return;
+		}
+		p = &parent->rb_right;
+	}
+insert:
+	/* Insert segment into RB tree. */
+	rb_link_node(&skb->rbnode, parent, p);
+	rb_insert_color(&skb->rbnode, &msk->out_of_order_queue);
+
+merge_right:
+	/* Remove other segments covered by skb. */
+	while ((skb1 = skb_rb_next(skb)) != NULL) {
+		if (before64(end_seq, MPTCP_SKB_CB(skb1)->end_seq))
+			break;
+		rb_erase(&skb1->rbnode, &msk->out_of_order_queue);
+		mptcp_drop(sk, skb1);
+	}
+	/* If there is no skb after us, we are the last_skb ! */
+	if (!skb1)
+		msk->ooo_last_skb = skb;
+
+end:
+	skb_condense(skb);
+	skb_set_owner_r(skb, sk);
+}
+
+static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk,
+			     struct sk_buff *skb, unsigned int offset,
+			     size_t copy_len)
+{
+	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
 	struct sock *sk = (struct sock *)msk;
 	struct sk_buff *tail;
 
@@ -137,15 +256,35 @@ static void __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk,
 
 	skb_ext_reset(skb);
 	skb_orphan(skb);
+
+	/* the skb map_seq accounts for the skb offset:
+	 * mptcp_subflow_get_mapped_dsn() is based on the current tp->copied_seq
+	 * value
+	 */
+	MPTCP_SKB_CB(skb)->map_seq = mptcp_subflow_get_mapped_dsn(subflow);
+	MPTCP_SKB_CB(skb)->end_seq = MPTCP_SKB_CB(skb)->map_seq + copy_len;
 	MPTCP_SKB_CB(skb)->offset = offset;
-	msk->ack_seq += copy_len;
 
-	tail = skb_peek_tail(&sk->sk_receive_queue);
-	if (tail && mptcp_try_coalesce(sk, tail, skb))
-		return;
+	if (MPTCP_SKB_CB(skb)->map_seq == msk->ack_seq) {
+		/* in sequence */
+		msk->ack_seq += copy_len;
+		tail = skb_peek_tail(&sk->sk_receive_queue);
+		if (tail && mptcp_try_coalesce(sk, tail, skb))
+			return true;
 
-	skb_set_owner_r(skb, sk);
-	__skb_queue_tail(&sk->sk_receive_queue, skb);
+		skb_set_owner_r(skb, sk);
+		__skb_queue_tail(&sk->sk_receive_queue, skb);
+		return true;
+	} else if (after64(MPTCP_SKB_CB(skb)->map_seq, msk->ack_seq)) {
+		mptcp_data_queue_ofo(msk, skb);
+		return false;
+	}
+
+	/* old data, keep it simple and drop the whole pkt, sender
+	 * will retransmit as needed, if needed.
+	 */
+	mptcp_drop(sk, skb);
+	return false;
 }
 
 static void mptcp_stop_timer(struct sock *sk)
@@ -156,28 +295,6 @@ static void mptcp_stop_timer(struct sock *sk)
 	mptcp_sk(sk)->timer_ival = 0;
 }
 
-/* both sockets must be locked */
-static bool mptcp_subflow_dsn_valid(const struct mptcp_sock *msk,
-				    struct sock *ssk)
-{
-	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
-	u64 dsn = mptcp_subflow_get_mapped_dsn(subflow);
-
-	/* revalidate data sequence number.
-	 *
-	 * mptcp_subflow_data_available() is usually called
-	 * without msk lock.  Its unlikely (but possible)
-	 * that msk->ack_seq has been advanced since the last
-	 * call found in-sequence data.
-	 */
-	if (likely(dsn == msk->ack_seq))
-		return true;
-
-	subflow->data_avail = 0;
-	mptcp_subflow_data_available(ssk);
-	return subflow->data_avail == MPTCP_SUBFLOW_DATA_AVAIL;
-}
-
 static void mptcp_check_data_fin_ack(struct sock *sk)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
@@ -321,18 +438,7 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk,
 	struct tcp_sock *tp;
 	bool done = false;
 
-	pr_debug("msk=%p ssk=%p data avail=%d valid=%d empty=%d",
-		 msk, ssk, subflow->data_avail,
-		 mptcp_subflow_dsn_valid(msk, ssk),
-		 !skb_peek(&ssk->sk_receive_queue));
-	if (subflow->data_avail == MPTCP_SUBFLOW_OOO_DATA) {
-		mptcp_subflow_discard_data(ssk, subflow->map_data_len);
-		return false;
-	}
-
-	if (!mptcp_subflow_dsn_valid(msk, ssk))
-		return false;
-
+	pr_debug("msk=%p ssk=%p", msk, ssk);
 	tp = tcp_sk(ssk);
 	do {
 		u32 map_remaining, offset;
@@ -370,9 +476,9 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk,
 			if (tp->urg_data)
 				done = true;
 
-			__mptcp_move_skb(msk, ssk, skb, offset, len);
+			if (__mptcp_move_skb(msk, ssk, skb, offset, len))
+				moved += len;
 			seq += len;
-			moved += len;
 
 			if (WARN_ON_ONCE(map_remaining < len))
 				break;
@@ -393,18 +499,47 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk,
 
 	*bytes += moved;
 
-	/* If the moves have caught up with the DATA_FIN sequence number
-	 * it's time to ack the DATA_FIN and change socket state, but
-	 * this is not a good place to change state. Let the workqueue
-	 * do it.
-	 */
-	if (mptcp_pending_data_fin(sk, NULL) &&
-	    schedule_work(&msk->work))
-		sock_hold(sk);
-
 	return done;
 }
 
+static bool mptcp_ofo_queue(struct mptcp_sock *msk)
+{
+	struct sock *sk = (struct sock *)msk;
+	struct sk_buff *skb, *tail;
+	bool moved = false;
+	struct rb_node *p;
+	u64 end_seq;
+
+	p = rb_first(&msk->out_of_order_queue);
+	while (p) {
+		skb = rb_to_skb(p);
+		if (after64(MPTCP_SKB_CB(skb)->map_seq, msk->ack_seq))
+			break;
+
+		p = rb_next(p);
+		rb_erase(&skb->rbnode, &msk->out_of_order_queue);
+
+		if (unlikely(!after64(MPTCP_SKB_CB(skb)->end_seq,
+				      msk->ack_seq))) {
+			mptcp_drop(sk, skb);
+			continue;
+		}
+
+		end_seq = MPTCP_SKB_CB(skb)->end_seq;
+		tail = skb_peek_tail(&sk->sk_receive_queue);
+		if (!tail || !mptcp_ooo_try_coalesce(msk, tail, skb)) {
+			int delta = msk->ack_seq - MPTCP_SKB_CB(skb)->map_seq;
+
+			/* skip overlapping data, if any */
+			MPTCP_SKB_CB(skb)->offset += delta;
+			__skb_queue_tail(&sk->sk_receive_queue, skb);
+		}
+		msk->ack_seq = end_seq;
+		moved = true;
+	}
+	return moved;
+}
+
 /* In most cases we will be able to lock the mptcp socket.  If its already
  * owned, we need to defer to the work queue to avoid ABBA deadlock.
  */
@@ -420,8 +555,19 @@ static bool move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk)
 		return false;
 
 	/* must re-check after taking the lock */
-	if (!READ_ONCE(sk->sk_lock.owned))
+	if (!READ_ONCE(sk->sk_lock.owned)) {
 		__mptcp_move_skbs_from_subflow(msk, ssk, &moved);
+		mptcp_ofo_queue(msk);
+
+		/* If the moves have caught up with the DATA_FIN sequence number
+		 * it's time to ack the DATA_FIN and change socket state, but
+		 * this is not a good place to change state. Let the workqueue
+		 * do it.
+		 */
+		if (mptcp_pending_data_fin(sk, NULL) &&
+		    schedule_work(&msk->work))
+			sock_hold(sk);
+	}
 
 	spin_unlock_bh(&sk->sk_lock.slock);
 
@@ -1218,7 +1364,11 @@ static bool __mptcp_move_skbs(struct mptcp_sock *msk)
 		release_sock(ssk);
 	} while (!done);
 
-	return moved > 0;
+	if (mptcp_ofo_queue(msk) || moved > 0) {
+		mptcp_check_data_fin((struct sock *)msk);
+		return true;
+	}
+	return false;
 }
 
 static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
@@ -1530,6 +1680,7 @@ static int __mptcp_init_sock(struct sock *sk)
 	INIT_LIST_HEAD(&msk->rtx_queue);
 	__set_bit(MPTCP_SEND_SPACE, &msk->flags);
 	INIT_WORK(&msk->work, mptcp_worker);
+	msk->out_of_order_queue = RB_ROOT;
 
 	msk->first = NULL;
 	inet_csk(sk)->icsk_sync_mss = mptcp_sync_mss;
@@ -1869,6 +2020,7 @@ static void mptcp_destroy(struct sock *sk)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
 
+	skb_rbtree_purge(&msk->out_of_order_queue);
 	mptcp_token_destroy(msk);
 	if (msk->cached_ext)
 		__skb_ext_put(msk->cached_ext);
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 794997852c5e..0a602acf1f3d 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -204,6 +204,8 @@ struct mptcp_sock {
 	bool		snd_data_fin_enable;
 	spinlock_t	join_list_lock;
 	struct work_struct work;
+	struct sk_buff  *ooo_last_skb;
+	struct rb_root  out_of_order_queue;
 	struct list_head conn_list;
 	struct list_head rtx_queue;
 	struct list_head join_list;
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 071ee54b3c9f..0b1d73a69daf 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -434,6 +434,7 @@ static void mptcp_sock_destruct(struct sock *sk)
 		sock_orphan(sk);
 	}
 
+	skb_rbtree_purge(&mptcp_sk(sk)->out_of_order_queue);
 	mptcp_token_destroy(mptcp_sk(sk));
 	inet_sock_destruct(sk);
 }

From 04e4cd4f7ca4600409a898fe0abc318372c4c1ab Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Mon, 14 Sep 2020 10:01:13 +0200
Subject: [PATCH 07/13] mptcp: cleanup mptcp_subflow_discard_data()

There is no need to use the tcp_read_sock(), we can
simply drop the skb. Additionally try to look at the
next buffer for in order data.

This both simplifies the code and avoid unneeded indirect
calls.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mptcp/protocol.h |  1 -
 net/mptcp/subflow.c  | 56 ++++++++++----------------------------------
 2 files changed, 13 insertions(+), 44 deletions(-)

diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 0a602acf1f3d..26f5f81f3f4c 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -355,7 +355,6 @@ int mptcp_is_enabled(struct net *net);
 void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow,
 				     struct mptcp_options_received *mp_opt);
 bool mptcp_subflow_data_available(struct sock *sk);
-int mptcp_subflow_discard_data(struct sock *sk, unsigned int limit);
 void __init mptcp_subflow_init(void);
 
 /* called with sk socket lock held */
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 0b1d73a69daf..6eb2fc0a8ebb 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -805,50 +805,22 @@ validate_seq:
 	return MAPPING_OK;
 }
 
-static int subflow_read_actor(read_descriptor_t *desc,
-			      struct sk_buff *skb,
-			      unsigned int offset, size_t len)
-{
-	size_t copy_len = min(desc->count, len);
-
-	desc->count -= copy_len;
-
-	pr_debug("flushed %zu bytes, %zu left", copy_len, desc->count);
-	return copy_len;
-}
-
-int mptcp_subflow_discard_data(struct sock *ssk, unsigned int limit)
+static void mptcp_subflow_discard_data(struct sock *ssk, struct sk_buff *skb,
+				       unsigned int limit)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
-	u32 map_remaining;
-	size_t delta;
+	bool fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN;
+	u32 incr;
 
-	map_remaining = subflow->map_data_len -
-			mptcp_subflow_get_map_offset(subflow);
-	delta = min_t(size_t, limit, map_remaining);
+	incr = limit >= skb->len ? skb->len + fin : limit;
 
-	/* discard mapped data */
-	pr_debug("discarding %zu bytes, current map len=%d", delta,
-		 map_remaining);
-	if (delta) {
-		read_descriptor_t desc = {
-			.count = delta,
-		};
-		int ret;
-
-		ret = tcp_read_sock(ssk, &desc, subflow_read_actor);
-		if (ret < 0) {
-			ssk->sk_err = -ret;
-			return ret;
-		}
-		if (ret < delta)
-			return 0;
-		if (delta == map_remaining) {
-			subflow->data_avail = 0;
-			subflow->map_valid = 0;
-		}
-	}
-	return 0;
+	pr_debug("discarding=%d len=%d seq=%d", incr, skb->len,
+		 subflow->map_subflow_seq);
+	tcp_sk(ssk)->copied_seq += incr;
+	if (!before(tcp_sk(ssk)->copied_seq, TCP_SKB_CB(skb)->end_seq))
+		sk_eat_skb(ssk, skb);
+	if (mptcp_subflow_get_map_offset(subflow) >= subflow->map_data_len)
+		subflow->map_valid = 0;
 }
 
 static bool subflow_check_data_avail(struct sock *ssk)
@@ -923,9 +895,7 @@ static bool subflow_check_data_avail(struct sock *ssk)
 		/* only accept in-sequence mapping. Old values are spurious
 		 * retransmission
 		 */
-		if (mptcp_subflow_discard_data(ssk, old_ack - ack_seq))
-			goto fatal;
-		return false;
+		mptcp_subflow_discard_data(ssk, skb, old_ack - ack_seq);
 	}
 	return true;
 

From 06242e44b9fbd59be0bd4a4ed82b38f8f2c3f4b2 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Mon, 14 Sep 2020 10:01:14 +0200
Subject: [PATCH 08/13] mptcp: add OoO related mibs

Add a bunch of MPTCP mibs related to MPTCP OoO data
processing.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mptcp/mib.c      |  5 +++++
 net/mptcp/mib.h      |  5 +++++
 net/mptcp/protocol.c | 24 +++++++++++++++++++++++-
 net/mptcp/subflow.c  |  1 +
 4 files changed, 34 insertions(+), 1 deletion(-)

diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c
index 0a6a15f3456d..056986c7a228 100644
--- a/net/mptcp/mib.c
+++ b/net/mptcp/mib.c
@@ -22,6 +22,11 @@ static const struct snmp_mib mptcp_snmp_list[] = {
 	SNMP_MIB_ITEM("MPJoinAckHMacFailure", MPTCP_MIB_JOINACKMAC),
 	SNMP_MIB_ITEM("DSSNotMatching", MPTCP_MIB_DSSNOMATCH),
 	SNMP_MIB_ITEM("InfiniteMapRx", MPTCP_MIB_INFINITEMAPRX),
+	SNMP_MIB_ITEM("OFOQueueTail", MPTCP_MIB_OFOQUEUETAIL),
+	SNMP_MIB_ITEM("OFOQueue", MPTCP_MIB_OFOQUEUE),
+	SNMP_MIB_ITEM("OFOMerge", MPTCP_MIB_OFOMERGE),
+	SNMP_MIB_ITEM("NoDSSInWindow", MPTCP_MIB_NODSSWINDOW),
+	SNMP_MIB_ITEM("DuplicateData", MPTCP_MIB_DUPDATA),
 	SNMP_MIB_SENTINEL
 };
 
diff --git a/net/mptcp/mib.h b/net/mptcp/mib.h
index d7de340fc997..937a177729f1 100644
--- a/net/mptcp/mib.h
+++ b/net/mptcp/mib.h
@@ -15,6 +15,11 @@ enum linux_mptcp_mib_field {
 	MPTCP_MIB_JOINACKMAC,		/* HMAC was wrong on ACK + MP_JOIN */
 	MPTCP_MIB_DSSNOMATCH,		/* Received a new mapping that did not match the previous one */
 	MPTCP_MIB_INFINITEMAPRX,	/* Received an infinite mapping */
+	MPTCP_MIB_OFOQUEUETAIL,	/* Segments inserted into OoO queue tail */
+	MPTCP_MIB_OFOQUEUE,		/* Segments inserted into OoO queue */
+	MPTCP_MIB_OFOMERGE,		/* Segments merged in OoO queue */
+	MPTCP_MIB_NODSSWINDOW,		/* Segments not in MPTCP windows */
+	MPTCP_MIB_DUPDATA,		/* Segments discarded due to duplicate DSS */
 	__MPTCP_MIB_MAX
 };
 
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 6fbfbab51660..ec9c38d3acc7 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -128,6 +128,9 @@ static bool mptcp_try_coalesce(struct sock *sk, struct sk_buff *to,
 	    !skb_try_coalesce(to, from, &fragstolen, &delta))
 		return false;
 
+	pr_debug("colesced seq %llx into %llx new len %d new end seq %llx",
+		 MPTCP_SKB_CB(from)->map_seq, MPTCP_SKB_CB(to)->map_seq,
+		 to->len, MPTCP_SKB_CB(from)->end_seq);
 	MPTCP_SKB_CB(to)->end_seq = MPTCP_SKB_CB(from)->end_seq;
 	kfree_skb_partial(from, fragstolen);
 	atomic_add(delta, &sk->sk_rmem_alloc);
@@ -160,13 +163,17 @@ static void mptcp_data_queue_ofo(struct mptcp_sock *msk, struct sk_buff *skb)
 	max_seq = tcp_space(sk);
 	max_seq = max_seq > 0 ? max_seq + msk->ack_seq : msk->ack_seq;
 
+	pr_debug("msk=%p seq=%llx limit=%llx empty=%d", msk, seq, max_seq,
+		 RB_EMPTY_ROOT(&msk->out_of_order_queue));
 	if (after64(seq, max_seq)) {
 		/* out of window */
 		mptcp_drop(sk, skb);
+		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_NODSSWINDOW);
 		return;
 	}
 
 	p = &msk->out_of_order_queue.rb_node;
+	MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_OFOQUEUE);
 	if (RB_EMPTY_ROOT(&msk->out_of_order_queue)) {
 		rb_link_node(&skb->rbnode, NULL, p);
 		rb_insert_color(&skb->rbnode, &msk->out_of_order_queue);
@@ -177,11 +184,15 @@ static void mptcp_data_queue_ofo(struct mptcp_sock *msk, struct sk_buff *skb)
 	/* with 2 subflows, adding at end of ooo queue is quite likely
 	 * Use of ooo_last_skb avoids the O(Log(N)) rbtree lookup.
 	 */
-	if (mptcp_ooo_try_coalesce(msk, msk->ooo_last_skb, skb))
+	if (mptcp_ooo_try_coalesce(msk, msk->ooo_last_skb, skb)) {
+		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_OFOMERGE);
+		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_OFOQUEUETAIL);
 		return;
+	}
 
 	/* Can avoid an rbtree lookup if we are adding skb after ooo_last_skb */
 	if (!before64(seq, MPTCP_SKB_CB(msk->ooo_last_skb)->end_seq)) {
+		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_OFOQUEUETAIL);
 		parent = &msk->ooo_last_skb->rbnode;
 		p = &parent->rb_right;
 		goto insert;
@@ -200,6 +211,7 @@ static void mptcp_data_queue_ofo(struct mptcp_sock *msk, struct sk_buff *skb)
 			if (!after64(end_seq, MPTCP_SKB_CB(skb1)->end_seq)) {
 				/* All the bits are present. Drop. */
 				mptcp_drop(sk, skb);
+				MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_DUPDATA);
 				return;
 			}
 			if (after64(seq, MPTCP_SKB_CB(skb1)->map_seq)) {
@@ -215,13 +227,16 @@ static void mptcp_data_queue_ofo(struct mptcp_sock *msk, struct sk_buff *skb)
 				rb_replace_node(&skb1->rbnode, &skb->rbnode,
 						&msk->out_of_order_queue);
 				mptcp_drop(sk, skb1);
+				MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_DUPDATA);
 				goto merge_right;
 			}
 		} else if (mptcp_ooo_try_coalesce(msk, skb1, skb)) {
+			MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_OFOMERGE);
 			return;
 		}
 		p = &parent->rb_right;
 	}
+
 insert:
 	/* Insert segment into RB tree. */
 	rb_link_node(&skb->rbnode, parent, p);
@@ -234,6 +249,7 @@ merge_right:
 			break;
 		rb_erase(&skb1->rbnode, &msk->out_of_order_queue);
 		mptcp_drop(sk, skb1);
+		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_DUPDATA);
 	}
 	/* If there is no skb after us, we are the last_skb ! */
 	if (!skb1)
@@ -283,6 +299,7 @@ static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk,
 	/* old data, keep it simple and drop the whole pkt, sender
 	 * will retransmit as needed, if needed.
 	 */
+	MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_DUPDATA);
 	mptcp_drop(sk, skb);
 	return false;
 }
@@ -511,6 +528,7 @@ static bool mptcp_ofo_queue(struct mptcp_sock *msk)
 	u64 end_seq;
 
 	p = rb_first(&msk->out_of_order_queue);
+	pr_debug("msk=%p empty=%d", msk, RB_EMPTY_ROOT(&msk->out_of_order_queue));
 	while (p) {
 		skb = rb_to_skb(p);
 		if (after64(MPTCP_SKB_CB(skb)->map_seq, msk->ack_seq))
@@ -522,6 +540,7 @@ static bool mptcp_ofo_queue(struct mptcp_sock *msk)
 		if (unlikely(!after64(MPTCP_SKB_CB(skb)->end_seq,
 				      msk->ack_seq))) {
 			mptcp_drop(sk, skb);
+			MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_DUPDATA);
 			continue;
 		}
 
@@ -531,6 +550,9 @@ static bool mptcp_ofo_queue(struct mptcp_sock *msk)
 			int delta = msk->ack_seq - MPTCP_SKB_CB(skb)->map_seq;
 
 			/* skip overlapping data, if any */
+			pr_debug("uncoalesced seq=%llx ack seq=%llx delta=%d",
+				 MPTCP_SKB_CB(skb)->map_seq, msk->ack_seq,
+				 delta);
 			MPTCP_SKB_CB(skb)->offset += delta;
 			__skb_queue_tail(&sk->sk_receive_queue, skb);
 		}
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 6eb2fc0a8ebb..8c9418d1901b 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -816,6 +816,7 @@ static void mptcp_subflow_discard_data(struct sock *ssk, struct sk_buff *skb,
 
 	pr_debug("discarding=%d len=%d seq=%d", incr, skb->len,
 		 subflow->map_subflow_seq);
+	MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DUPDATA);
 	tcp_sk(ssk)->copied_seq += incr;
 	if (!before(tcp_sk(ssk)->copied_seq, TCP_SKB_CB(skb)->end_seq))
 		sk_eat_skb(ssk, skb);

From ef0da3b8a2f18f59ea310ce27696c431eeb57eab Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Mon, 14 Sep 2020 10:01:15 +0200
Subject: [PATCH 09/13] mptcp: move address attribute into mptcp_addr_info

So that can be accessed easily from the subflow creation
helper. No functional change intended.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mptcp/pm_netlink.c | 39 ++++++++++++++++++++-------------------
 net/mptcp/protocol.h   |  5 +++--
 net/mptcp/subflow.c    |  5 ++---
 3 files changed, 25 insertions(+), 24 deletions(-)

diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 2c208d2e65cd..6947f4fee6b9 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -23,8 +23,6 @@ static int pm_nl_pernet_id;
 
 struct mptcp_pm_addr_entry {
 	struct list_head	list;
-	unsigned int		flags;
-	int			ifindex;
 	struct mptcp_addr_info	addr;
 	struct rcu_head		rcu;
 };
@@ -119,7 +117,7 @@ select_local_address(const struct pm_nl_pernet *pernet,
 	rcu_read_lock();
 	spin_lock_bh(&msk->join_list_lock);
 	list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) {
-		if (!(entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW))
+		if (!(entry->addr.flags & MPTCP_PM_ADDR_FLAG_SUBFLOW))
 			continue;
 
 		/* avoid any address already in use by subflows and
@@ -150,7 +148,7 @@ select_signal_address(struct pm_nl_pernet *pernet, unsigned int pos)
 	 * can lead to additional addresses not being announced.
 	 */
 	list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) {
-		if (!(entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL))
+		if (!(entry->addr.flags & MPTCP_PM_ADDR_FLAG_SIGNAL))
 			continue;
 		if (i++ == pos) {
 			ret = entry;
@@ -210,8 +208,7 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
 			msk->pm.subflows++;
 			check_work_pending(msk);
 			spin_unlock_bh(&msk->pm.lock);
-			__mptcp_subflow_connect(sk, local->ifindex,
-						&local->addr, &remote);
+			__mptcp_subflow_connect(sk, &local->addr, &remote);
 			spin_lock_bh(&msk->pm.lock);
 			return;
 		}
@@ -257,13 +254,13 @@ void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk)
 	local.family = remote.family;
 
 	spin_unlock_bh(&msk->pm.lock);
-	__mptcp_subflow_connect((struct sock *)msk, 0, &local, &remote);
+	__mptcp_subflow_connect((struct sock *)msk, &local, &remote);
 	spin_lock_bh(&msk->pm.lock);
 }
 
 static bool address_use_port(struct mptcp_pm_addr_entry *entry)
 {
-	return (entry->flags &
+	return (entry->addr.flags &
 		(MPTCP_PM_ADDR_FLAG_SIGNAL | MPTCP_PM_ADDR_FLAG_SUBFLOW)) ==
 		MPTCP_PM_ADDR_FLAG_SIGNAL;
 }
@@ -293,9 +290,9 @@ static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet,
 			goto out;
 	}
 
-	if (entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL)
+	if (entry->addr.flags & MPTCP_PM_ADDR_FLAG_SIGNAL)
 		pernet->add_addr_signal_max++;
-	if (entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW)
+	if (entry->addr.flags & MPTCP_PM_ADDR_FLAG_SUBFLOW)
 		pernet->local_addr_max++;
 
 	entry->addr.id = pernet->next_id++;
@@ -345,8 +342,9 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc)
 	if (!entry)
 		return -ENOMEM;
 
-	entry->flags = 0;
 	entry->addr = skc_local;
+	entry->addr.ifindex = 0;
+	entry->addr.flags = 0;
 	ret = mptcp_pm_nl_append_new_local_addr(pernet, entry);
 	if (ret < 0)
 		kfree(entry);
@@ -460,14 +458,17 @@ static int mptcp_pm_parse_addr(struct nlattr *attr, struct genl_info *info,
 		entry->addr.addr.s_addr = nla_get_in_addr(tb[addr_addr]);
 
 skip_family:
-	if (tb[MPTCP_PM_ADDR_ATTR_IF_IDX])
-		entry->ifindex = nla_get_s32(tb[MPTCP_PM_ADDR_ATTR_IF_IDX]);
+	if (tb[MPTCP_PM_ADDR_ATTR_IF_IDX]) {
+		u32 val = nla_get_s32(tb[MPTCP_PM_ADDR_ATTR_IF_IDX]);
+
+		entry->addr.ifindex = val;
+	}
 
 	if (tb[MPTCP_PM_ADDR_ATTR_ID])
 		entry->addr.id = nla_get_u8(tb[MPTCP_PM_ADDR_ATTR_ID]);
 
 	if (tb[MPTCP_PM_ADDR_ATTR_FLAGS])
-		entry->flags = nla_get_u32(tb[MPTCP_PM_ADDR_ATTR_FLAGS]);
+		entry->addr.flags = nla_get_u32(tb[MPTCP_PM_ADDR_ATTR_FLAGS]);
 
 	return 0;
 }
@@ -535,9 +536,9 @@ static int mptcp_nl_cmd_del_addr(struct sk_buff *skb, struct genl_info *info)
 		ret = -EINVAL;
 		goto out;
 	}
-	if (entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL)
+	if (entry->addr.flags & MPTCP_PM_ADDR_FLAG_SIGNAL)
 		pernet->add_addr_signal_max--;
-	if (entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW)
+	if (entry->addr.flags & MPTCP_PM_ADDR_FLAG_SUBFLOW)
 		pernet->local_addr_max--;
 
 	pernet->addrs--;
@@ -593,10 +594,10 @@ static int mptcp_nl_fill_addr(struct sk_buff *skb,
 		goto nla_put_failure;
 	if (nla_put_u8(skb, MPTCP_PM_ADDR_ATTR_ID, addr->id))
 		goto nla_put_failure;
-	if (nla_put_u32(skb, MPTCP_PM_ADDR_ATTR_FLAGS, entry->flags))
+	if (nla_put_u32(skb, MPTCP_PM_ADDR_ATTR_FLAGS, entry->addr.flags))
 		goto nla_put_failure;
-	if (entry->ifindex &&
-	    nla_put_s32(skb, MPTCP_PM_ADDR_ATTR_IF_IDX, entry->ifindex))
+	if (entry->addr.ifindex &&
+	    nla_put_s32(skb, MPTCP_PM_ADDR_ATTR_IF_IDX, entry->addr.ifindex))
 		goto nla_put_failure;
 
 	if (addr->family == AF_INET &&
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 26f5f81f3f4c..cfa5e1b9521b 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -140,6 +140,8 @@ struct mptcp_addr_info {
 	sa_family_t		family;
 	__be16			port;
 	u8			id;
+	u8			flags;
+	int			ifindex;
 	union {
 		struct in_addr addr;
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
@@ -358,8 +360,7 @@ bool mptcp_subflow_data_available(struct sock *sk);
 void __init mptcp_subflow_init(void);
 
 /* called with sk socket lock held */
-int __mptcp_subflow_connect(struct sock *sk, int ifindex,
-			    const struct mptcp_addr_info *loc,
+int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc,
 			    const struct mptcp_addr_info *remote);
 int mptcp_subflow_create_socket(struct sock *sk, struct socket **new_sock);
 
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 8c9418d1901b..ae3eeb9bb191 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -1035,8 +1035,7 @@ static void mptcp_info2sockaddr(const struct mptcp_addr_info *info,
 #endif
 }
 
-int __mptcp_subflow_connect(struct sock *sk, int ifindex,
-			    const struct mptcp_addr_info *loc,
+int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc,
 			    const struct mptcp_addr_info *remote)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
@@ -1080,7 +1079,7 @@ int __mptcp_subflow_connect(struct sock *sk, int ifindex,
 	if (loc->family == AF_INET6)
 		addrlen = sizeof(struct sockaddr_in6);
 #endif
-	ssk->sk_bound_dev_if = ifindex;
+	ssk->sk_bound_dev_if = loc->ifindex;
 	err = kernel_bind(sf, (struct sockaddr *)&addr, addrlen);
 	if (err)
 		goto failed;

From 4596a2c1b7f55b8dac9ef4d8724cbef6e11eb74c Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Mon, 14 Sep 2020 10:01:16 +0200
Subject: [PATCH 10/13] mptcp: allow creating non-backup subflows

Currently the 'backup' attribute of local endpoint
is ignored. Let's use it for the MP_JOIN handshake

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mptcp/subflow.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index ae3eeb9bb191..8be401349d9f 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -20,6 +20,7 @@
 #include <net/ip6_route.h>
 #endif
 #include <net/mptcp.h>
+#include <uapi/linux/mptcp.h>
 #include "protocol.h"
 #include "mib.h"
 
@@ -1090,7 +1091,7 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc,
 	subflow->remote_token = remote_token;
 	subflow->local_id = local_id;
 	subflow->request_join = 1;
-	subflow->request_bkup = 1;
+	subflow->request_bkup = !!(loc->flags & MPTCP_PM_ADDR_FLAG_BACKUP);
 	mptcp_info2sockaddr(remote, &addr);
 
 	err = kernel_connect(sf, (struct sockaddr *)&addr, addrlen, O_NONBLOCK);

From d5f49190def61c47b2faff170ba8fbc48bac4371 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Mon, 14 Sep 2020 10:01:17 +0200
Subject: [PATCH 11/13] mptcp: allow picking different xmit subflows

Update the scheduler to less trivial heuristic: cache
the last used subflow, and try to send on it a reasonably
long burst of data.

When the burst or the subflow send space is exhausted, pick
the subflow with the lower ratio between write space and
send buffer - that is, the subflow with the greater relative
amount of free space.

v1 -> v2:
 - fix 32 bit build breakage due to 64bits div
 - fix checkpath issues (uint64_t -> u64)

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mptcp/protocol.c | 123 +++++++++++++++++++++++++++++++++++--------
 net/mptcp/protocol.h |   6 ++-
 2 files changed, 105 insertions(+), 24 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index ec9c38d3acc7..d7af96a900c4 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1031,41 +1031,105 @@ static void mptcp_nospace(struct mptcp_sock *msk)
 	}
 }
 
+static bool mptcp_subflow_active(struct mptcp_subflow_context *subflow)
+{
+	struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+
+	/* can't send if JOIN hasn't completed yet (i.e. is usable for mptcp) */
+	if (subflow->request_join && !subflow->fully_established)
+		return false;
+
+	/* only send if our side has not closed yet */
+	return ((1 << ssk->sk_state) & (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT));
+}
+
+#define MPTCP_SEND_BURST_SIZE		((1 << 16) - \
+					 sizeof(struct tcphdr) - \
+					 MAX_TCP_OPTION_SPACE - \
+					 sizeof(struct ipv6hdr) - \
+					 sizeof(struct frag_hdr))
+
+struct subflow_send_info {
+	struct sock *ssk;
+	u64 ratio;
+};
+
 static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk,
 					   u32 *sndbuf)
 {
+	struct subflow_send_info send_info[2];
 	struct mptcp_subflow_context *subflow;
-	struct sock *sk = (struct sock *)msk;
-	struct sock *backup = NULL;
-	bool free;
+	int i, nr_active = 0;
+	struct sock *ssk;
+	u64 ratio;
+	u32 pace;
 
-	sock_owned_by_me(sk);
+	sock_owned_by_me((struct sock *)msk);
 
 	*sndbuf = 0;
 	if (!mptcp_ext_cache_refill(msk))
 		return NULL;
 
-	mptcp_for_each_subflow(msk, subflow) {
-		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
-
-		free = sk_stream_is_writeable(subflow->tcp_sock);
-		if (!free) {
-			mptcp_nospace(msk);
+	if (__mptcp_check_fallback(msk)) {
+		if (!msk->first)
 			return NULL;
-		}
-
-		*sndbuf = max(tcp_sk(ssk)->snd_wnd, *sndbuf);
-		if (subflow->backup) {
-			if (!backup)
-				backup = ssk;
-
-			continue;
-		}
-
-		return ssk;
+		*sndbuf = msk->first->sk_sndbuf;
+		return sk_stream_memory_free(msk->first) ? msk->first : NULL;
 	}
 
-	return backup;
+	/* re-use last subflow, if the burst allow that */
+	if (msk->last_snd && msk->snd_burst > 0 &&
+	    sk_stream_memory_free(msk->last_snd) &&
+	    mptcp_subflow_active(mptcp_subflow_ctx(msk->last_snd))) {
+		mptcp_for_each_subflow(msk, subflow) {
+			ssk =  mptcp_subflow_tcp_sock(subflow);
+			*sndbuf = max(tcp_sk(ssk)->snd_wnd, *sndbuf);
+		}
+		return msk->last_snd;
+	}
+
+	/* pick the subflow with the lower wmem/wspace ratio */
+	for (i = 0; i < 2; ++i) {
+		send_info[i].ssk = NULL;
+		send_info[i].ratio = -1;
+	}
+	mptcp_for_each_subflow(msk, subflow) {
+		ssk =  mptcp_subflow_tcp_sock(subflow);
+		if (!mptcp_subflow_active(subflow))
+			continue;
+
+		nr_active += !subflow->backup;
+		*sndbuf = max(tcp_sk(ssk)->snd_wnd, *sndbuf);
+		if (!sk_stream_memory_free(subflow->tcp_sock))
+			continue;
+
+		pace = READ_ONCE(ssk->sk_pacing_rate);
+		if (!pace)
+			continue;
+
+		ratio = div_u64((u64)READ_ONCE(ssk->sk_wmem_queued) << 32,
+				pace);
+		if (ratio < send_info[subflow->backup].ratio) {
+			send_info[subflow->backup].ssk = ssk;
+			send_info[subflow->backup].ratio = ratio;
+		}
+	}
+
+	pr_debug("msk=%p nr_active=%d ssk=%p:%lld backup=%p:%lld",
+		 msk, nr_active, send_info[0].ssk, send_info[0].ratio,
+		 send_info[1].ssk, send_info[1].ratio);
+
+	/* pick the best backup if no other subflow is active */
+	if (!nr_active)
+		send_info[0].ssk = send_info[1].ssk;
+
+	if (send_info[0].ssk) {
+		msk->last_snd = send_info[0].ssk;
+		msk->snd_burst = min_t(int, MPTCP_SEND_BURST_SIZE,
+				       sk_stream_wspace(msk->last_snd));
+		return msk->last_snd;
+	}
+	return NULL;
 }
 
 static void ssk_check_wmem(struct mptcp_sock *msk)
@@ -1160,6 +1224,10 @@ restart:
 			break;
 		}
 
+		/* burst can be negative, we will try move to the next subflow
+		 * at selection time, if possible.
+		 */
+		msk->snd_burst -= ret;
 		copied += ret;
 
 		tx_ok = msg_data_left(msg);
@@ -1375,6 +1443,11 @@ static bool __mptcp_move_skbs(struct mptcp_sock *msk)
 	unsigned int moved = 0;
 	bool done;
 
+	/* avoid looping forever below on racing close */
+	if (((struct sock *)msk)->sk_state == TCP_CLOSE)
+		return false;
+
+	__mptcp_flush_join_list(msk);
 	do {
 		struct sock *ssk = mptcp_subflow_recv_lookup(msk);
 
@@ -1539,9 +1612,15 @@ static struct sock *mptcp_subflow_get_retrans(const struct mptcp_sock *msk)
 
 	sock_owned_by_me((const struct sock *)msk);
 
+	if (__mptcp_check_fallback(msk))
+		return msk->first;
+
 	mptcp_for_each_subflow(msk, subflow) {
 		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
 
+		if (!mptcp_subflow_active(subflow))
+			continue;
+
 		/* still data outstanding at TCP level?  Don't retransmit. */
 		if (!tcp_write_queue_empty(ssk))
 			return NULL;
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index cfa5e1b9521b..493bd2c13bc6 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -196,6 +196,8 @@ struct mptcp_sock {
 	u64		write_seq;
 	u64		ack_seq;
 	u64		rcv_data_fin_seq;
+	struct sock	*last_snd;
+	int		snd_burst;
 	atomic64_t	snd_una;
 	unsigned long	timer_ival;
 	u32		token;
@@ -473,12 +475,12 @@ static inline bool before64(__u64 seq1, __u64 seq2)
 
 void mptcp_diag_subflow_init(struct tcp_ulp_ops *ops);
 
-static inline bool __mptcp_check_fallback(struct mptcp_sock *msk)
+static inline bool __mptcp_check_fallback(const struct mptcp_sock *msk)
 {
 	return test_bit(MPTCP_FALLBACK_DONE, &msk->flags);
 }
 
-static inline bool mptcp_check_fallback(struct sock *sk)
+static inline bool mptcp_check_fallback(const struct sock *sk)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
 	struct mptcp_sock *msk = mptcp_sk(subflow->conn);

From c76c6956566f974bac2470bd72fc22fb923e04a1 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Mon, 14 Sep 2020 10:01:18 +0200
Subject: [PATCH 12/13] mptcp: call tcp_cleanup_rbuf on subflows

That is needed to let the subflows announce promptly when new
space is available in the receive buffer.

tcp_cleanup_rbuf() is currently a static function, drop the
scope modifier and add a declaration in the TCP header.

Reviewed-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h    | 2 ++
 net/ipv4/tcp.c       | 2 +-
 net/mptcp/protocol.c | 6 ++++++
 net/mptcp/subflow.c  | 2 ++
 4 files changed, 11 insertions(+), 1 deletion(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index e85d564446c6..852f0d71dd40 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1414,6 +1414,8 @@ static inline int tcp_full_space(const struct sock *sk)
 	return tcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf));
 }
 
+void tcp_cleanup_rbuf(struct sock *sk, int copied);
+
 /* We provision sk_rcvbuf around 200% of sk_rcvlowat.
  * If 87.5 % (7/8) of the space has been consumed, we want to override
  * SO_RCVLOWAT constraint, since we are receiving skbs with too small
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 57a568875539..d3781b6087cb 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1527,7 +1527,7 @@ static int tcp_peek_sndq(struct sock *sk, struct msghdr *msg, int len)
  * calculation of whether or not we must ACK for the sake of
  * a window update.
  */
-static void tcp_cleanup_rbuf(struct sock *sk, int copied)
+void tcp_cleanup_rbuf(struct sock *sk, int copied)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	bool time_to_ack = false;
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index d7af96a900c4..ef0dd2f23482 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -515,6 +515,8 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk,
 	} while (more_data_avail);
 
 	*bytes += moved;
+	if (moved)
+		tcp_cleanup_rbuf(ssk, moved);
 
 	return done;
 }
@@ -1424,10 +1426,14 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied)
 			 */
 			mptcp_for_each_subflow(msk, subflow) {
 				struct sock *ssk;
+				bool slow;
 
 				ssk = mptcp_subflow_tcp_sock(subflow);
+				slow = lock_sock_fast(ssk);
 				WRITE_ONCE(ssk->sk_rcvbuf, rcvbuf);
 				tcp_sk(ssk)->window_clamp = window_clamp;
+				tcp_cleanup_rbuf(ssk, 1);
+				unlock_sock_fast(ssk, slow);
 			}
 		}
 	}
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 8be401349d9f..a2ae3087e24d 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -823,6 +823,8 @@ static void mptcp_subflow_discard_data(struct sock *ssk, struct sk_buff *skb,
 		sk_eat_skb(ssk, skb);
 	if (mptcp_subflow_get_map_offset(subflow) >= subflow->map_data_len)
 		subflow->map_valid = 0;
+	if (incr)
+		tcp_cleanup_rbuf(ssk, incr);
 }
 
 static bool subflow_check_data_avail(struct sock *ssk)

From 1a418cb8e888ccee29d5aca305cfdbae6cff2139 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Mon, 14 Sep 2020 10:01:19 +0200
Subject: [PATCH 13/13] mptcp: simult flow self-tests

Add a bunch of test-cases for multiple subflow xmit:
create multiple subflows simulating different links
condition via netem and verify that the msk is able
to use completely the aggregated bandwidth.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/mptcp/Makefile    |   3 +-
 .../selftests/net/mptcp/simult_flows.sh       | 293 ++++++++++++++++++
 2 files changed, 295 insertions(+), 1 deletion(-)
 create mode 100755 tools/testing/selftests/net/mptcp/simult_flows.sh

diff --git a/tools/testing/selftests/net/mptcp/Makefile b/tools/testing/selftests/net/mptcp/Makefile
index aa254aefc2c3..00bb158b4a5d 100644
--- a/tools/testing/selftests/net/mptcp/Makefile
+++ b/tools/testing/selftests/net/mptcp/Makefile
@@ -5,7 +5,8 @@ KSFT_KHDR_INSTALL := 1
 
 CFLAGS =  -Wall -Wl,--no-as-needed -O2 -g  -I$(top_srcdir)/usr/include
 
-TEST_PROGS := mptcp_connect.sh pm_netlink.sh mptcp_join.sh diag.sh
+TEST_PROGS := mptcp_connect.sh pm_netlink.sh mptcp_join.sh diag.sh \
+	      simult_flows.sh
 
 TEST_GEN_FILES = mptcp_connect pm_nl_ctl
 
diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh
new file mode 100755
index 000000000000..0d88225daa02
--- /dev/null
+++ b/tools/testing/selftests/net/mptcp/simult_flows.sh
@@ -0,0 +1,293 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+rndh=$(printf %x $sec)-$(mktemp -u XXXXXX)
+ns1="ns1-$rndh"
+ns2="ns2-$rndh"
+ns3="ns3-$rndh"
+capture=false
+ksft_skip=4
+timeout=30
+test_cnt=1
+ret=0
+bail=0
+
+usage() {
+	echo "Usage: $0 [ -b ] [ -c ] [ -d ]"
+	echo -e "\t-b: bail out after first error, otherwise runs al testcases"
+	echo -e "\t-c: capture packets for each test using tcpdump (default: no capture)"
+	echo -e "\t-d: debug this script"
+}
+
+cleanup()
+{
+	rm -f "$cin" "$cout"
+	rm -f "$sin" "$sout"
+	rm -f "$capout"
+
+	local netns
+	for netns in "$ns1" "$ns2" "$ns3";do
+		ip netns del $netns
+	done
+}
+
+ip -Version > /dev/null 2>&1
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not run test without ip tool"
+	exit $ksft_skip
+fi
+
+#  "$ns1"              ns2                    ns3
+#     ns1eth1    ns2eth1   ns2eth3      ns3eth1
+#            netem
+#     ns1eth2    ns2eth2
+#            netem
+
+setup()
+{
+	large=$(mktemp)
+	small=$(mktemp)
+	sout=$(mktemp)
+	cout=$(mktemp)
+	capout=$(mktemp)
+	size=$((2048 * 4096))
+	dd if=/dev/zero of=$small bs=4096 count=20 >/dev/null 2>&1
+	dd if=/dev/zero of=$large bs=4096 count=$((size / 4096)) >/dev/null 2>&1
+
+	trap cleanup EXIT
+
+	for i in "$ns1" "$ns2" "$ns3";do
+		ip netns add $i || exit $ksft_skip
+		ip -net $i link set lo up
+	done
+
+	ip link add ns1eth1 netns "$ns1" type veth peer name ns2eth1 netns "$ns2"
+	ip link add ns1eth2 netns "$ns1" type veth peer name ns2eth2 netns "$ns2"
+	ip link add ns2eth3 netns "$ns2" type veth peer name ns3eth1 netns "$ns3"
+
+	ip -net "$ns1" addr add 10.0.1.1/24 dev ns1eth1
+	ip -net "$ns1" addr add dead:beef:1::1/64 dev ns1eth1 nodad
+	ip -net "$ns1" link set ns1eth1 up mtu 1500
+	ip -net "$ns1" route add default via 10.0.1.2
+	ip -net "$ns1" route add default via dead:beef:1::2
+
+	ip -net "$ns1" addr add 10.0.2.1/24 dev ns1eth2
+	ip -net "$ns1" addr add dead:beef:2::1/64 dev ns1eth2 nodad
+	ip -net "$ns1" link set ns1eth2 up mtu 1500
+	ip -net "$ns1" route add default via 10.0.2.2 metric 101
+	ip -net "$ns1" route add default via dead:beef:2::2 metric 101
+
+	ip netns exec "$ns1" ./pm_nl_ctl limits 1 1
+	ip netns exec "$ns1" ./pm_nl_ctl add 10.0.2.1 dev ns1eth2 flags subflow
+	ip netns exec "$ns1" sysctl -q net.ipv4.conf.all.rp_filter=0
+
+	ip -net "$ns2" addr add 10.0.1.2/24 dev ns2eth1
+	ip -net "$ns2" addr add dead:beef:1::2/64 dev ns2eth1 nodad
+	ip -net "$ns2" link set ns2eth1 up mtu 1500
+
+	ip -net "$ns2" addr add 10.0.2.2/24 dev ns2eth2
+	ip -net "$ns2" addr add dead:beef:2::2/64 dev ns2eth2 nodad
+	ip -net "$ns2" link set ns2eth2 up mtu 1500
+
+	ip -net "$ns2" addr add 10.0.3.2/24 dev ns2eth3
+	ip -net "$ns2" addr add dead:beef:3::2/64 dev ns2eth3 nodad
+	ip -net "$ns2" link set ns2eth3 up mtu 1500
+	ip netns exec "$ns2" sysctl -q net.ipv4.ip_forward=1
+	ip netns exec "$ns2" sysctl -q net.ipv6.conf.all.forwarding=1
+
+	ip -net "$ns3" addr add 10.0.3.3/24 dev ns3eth1
+	ip -net "$ns3" addr add dead:beef:3::3/64 dev ns3eth1 nodad
+	ip -net "$ns3" link set ns3eth1 up mtu 1500
+	ip -net "$ns3" route add default via 10.0.3.2
+	ip -net "$ns3" route add default via dead:beef:3::2
+
+	ip netns exec "$ns3" ./pm_nl_ctl limits 1 1
+}
+
+# $1: ns, $2: port
+wait_local_port_listen()
+{
+	local listener_ns="${1}"
+	local port="${2}"
+
+	local port_hex i
+
+	port_hex="$(printf "%04X" "${port}")"
+	for i in $(seq 10); do
+		ip netns exec "${listener_ns}" cat /proc/net/tcp* | \
+			awk "BEGIN {rc=1} {if (\$2 ~ /:${port_hex}\$/ && \$4 ~ /0A/) {rc=0; exit}} END {exit rc}" &&
+			break
+		sleep 0.1
+	done
+}
+
+do_transfer()
+{
+	local cin=$1
+	local sin=$2
+	local max_time=$3
+	local port
+	port=$((10000+$test_cnt))
+	test_cnt=$((test_cnt+1))
+
+	:> "$cout"
+	:> "$sout"
+	:> "$capout"
+
+	local addr_port
+	addr_port=$(printf "%s:%d" ${connect_addr} ${port})
+
+	if $capture; then
+		local capuser
+		if [ -z $SUDO_USER ] ; then
+			capuser=""
+		else
+			capuser="-Z $SUDO_USER"
+		fi
+
+		local capfile="${rndh}-${port}"
+		local capopt="-i any -s 65535 -B 32768 ${capuser}"
+
+		ip netns exec ${ns3}  tcpdump ${capopt} -w "${capfile}-listener.pcap"  >> "${capout}" 2>&1 &
+		local cappid_listener=$!
+
+		ip netns exec ${ns1} tcpdump ${capopt} -w "${capfile}-connector.pcap" >> "${capout}" 2>&1 &
+		local cappid_connector=$!
+
+		sleep 1
+	fi
+
+	ip netns exec ${ns3} ./mptcp_connect -jt $timeout -l -p $port 0.0.0.0 < "$sin" > "$sout" &
+	local spid=$!
+
+	wait_local_port_listen "${ns3}" "${port}"
+
+	local start
+	start=$(date +%s%3N)
+	ip netns exec ${ns1} ./mptcp_connect -jt $timeout -p $port 10.0.3.3 < "$cin" > "$cout" &
+	local cpid=$!
+
+	wait $cpid
+	local retc=$?
+	wait $spid
+	local rets=$?
+
+	local stop
+	stop=$(date +%s%3N)
+
+	if $capture; then
+		sleep 1
+		kill ${cappid_listener}
+		kill ${cappid_connector}
+	fi
+
+	local duration
+	duration=$((stop-start))
+
+	cmp $sin $cout > /dev/null 2>&1
+	local cmps=$?
+	cmp $cin $sout > /dev/null 2>&1
+	local cmpc=$?
+
+	printf "%16s" "$duration max $max_time "
+	if [ $retc -eq 0 ] && [ $rets -eq 0 ] && \
+	   [ $cmpc -eq 0 ] && [ $cmps -eq 0 ] && \
+	   [ $duration -lt $max_time ]; then
+		echo "[ OK ]"
+		cat "$capout"
+		return 0
+	fi
+
+	echo " [ fail ]"
+	echo "client exit code $retc, server $rets" 1>&2
+	echo "\nnetns ${ns3} socket stat for $port:" 1>&2
+	ip netns exec ${ns3} ss -nita 1>&2 -o "sport = :$port"
+	echo "\nnetns ${ns1} socket stat for $port:" 1>&2
+	ip netns exec ${ns1} ss -nita 1>&2 -o "dport = :$port"
+	ls -l $sin $cout
+	ls -l $cin $sout
+
+	cat "$capout"
+	return 1
+}
+
+run_test()
+{
+	local rate1=$1
+	local rate2=$2
+	local delay1=$3
+	local delay2=$4
+	local lret
+	local dev
+	shift 4
+	local msg=$*
+
+	[ $delay1 -gt 0 ] && delay1="delay $delay1" || delay1=""
+	[ $delay2 -gt 0 ] && delay2="delay $delay2" || delay2=""
+
+	for dev in ns1eth1 ns1eth2; do
+		tc -n $ns1 qdisc del dev $dev root >/dev/null 2>&1
+	done
+	for dev in ns2eth1 ns2eth2; do
+		tc -n $ns2 qdisc del dev $dev root >/dev/null 2>&1
+	done
+	tc -n $ns1 qdisc add dev ns1eth1 root netem rate ${rate1}mbit $delay1
+	tc -n $ns1 qdisc add dev ns1eth2 root netem rate ${rate2}mbit $delay2
+	tc -n $ns2 qdisc add dev ns2eth1 root netem rate ${rate1}mbit $delay1
+	tc -n $ns2 qdisc add dev ns2eth2 root netem rate ${rate2}mbit $delay2
+
+	# time is measure in ms
+	local time=$((size * 8 * 1000 / (( $rate1 + $rate2) * 1024 *1024) ))
+
+	# mptcp_connect will do some sleeps to allow the mp_join handshake
+	# completion
+	time=$((time + 1350))
+
+	printf "%-50s" "$msg"
+	do_transfer $small $large $((time * 11 / 10))
+	lret=$?
+	if [ $lret -ne 0 ]; then
+		ret=$lret
+		[ $bail -eq 0 ] || exit $ret
+	fi
+
+	printf "%-50s" "$msg - reverse direction"
+	do_transfer $large $small $((time * 11 / 10))
+	lret=$?
+	if [ $lret -ne 0 ]; then
+		ret=$lret
+		[ $bail -eq 0 ] || exit $ret
+	fi
+}
+
+while getopts "bcdh" option;do
+	case "$option" in
+	"h")
+		usage $0
+		exit 0
+		;;
+	"b")
+		bail=1
+		;;
+	"c")
+		capture=true
+		;;
+	"d")
+		set -x
+		;;
+	"?")
+		usage $0
+		exit 1
+		;;
+	esac
+done
+
+setup
+run_test 10 10 0 0 "balanced bwidth"
+run_test 10 10 1 50 "balanced bwidth with unbalanced delay"
+
+# we still need some additional infrastructure to pass the following test-cases
+# run_test 30 10 0 0 "unbalanced bwidth"
+# run_test 30 10 1 50 "unbalanced bwidth with unbalanced delay"
+# run_test 30 10 50 1 "unbalanced bwidth with opposed, unbalanced delay"
+exit $ret