Merge branch 'mptcp-introduce-support-for-real-multipath-xmit'

Paolo Abeni says:

====================
mptcp: introduce support for real multipath xmit

This series enable MPTCP socket to transmit data on multiple subflows
concurrently in a load balancing scenario.

First the receive code path is refactored to better deal with out-of-order
data (patches 1-7). An RB-tree is introduced to queue MPTCP-level out-of-order
data, closely resembling the TCP level OoO handling.

When data is sent on multiple subflows, the peer can easily see OoO - "future"
data at the MPTCP level, especially if speeds, delay, or jitter are not
symmetric.

The other major change regards the netlink PM, which is extended to allow
creating non backup subflows in patches 9-11.

There are a few smaller additions, like the introduction of OoO related mibs,
send buffer autotuning and better ack handling.

Finally a bunch of new self-tests is introduced. The new feature is tested
ensuring that the B/W used by an MPTCP socket using multiple subflows matches
the link aggregated B/W - we use low B/W virtual links, to ensure the tests
are not CPU bounded.

v1 -> v2:
  - fix 32 bit build breakage
  - fix a bunch of checkpatch issues
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

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

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;

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
 };
 

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
 };
 

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 &&

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)
@@ -194,6 +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;
@@ -204,6 +208,8 @@ 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;
@@ -268,6 +274,12 @@ 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 +304,10 @@ 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;
@@ -350,8 +362,7 @@ 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);
 
@@ -464,12 +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);

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"
 
@@ -434,6 +435,7 @@ 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);
 }
@@ -804,16 +806,25 @@ static enum mapping_status get_mapping_status(struct sock *ssk,
 	return MAPPING_OK;
 }
 
-static int subflow_read_actor(read_descriptor_t *desc,
-			      struct sk_buff *skb,
-			      unsigned int offset, size_t len)
+static void mptcp_subflow_discard_data(struct sock *ssk, struct sk_buff *skb,
+				       unsigned int limit)
 {
-	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;
+	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
+	bool fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN;
+	u32 incr;
+
+	incr = limit >= skb->len ? skb->len + fin : limit;
+
+	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);
+	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)
@@ -825,13 +836,13 @@ 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;
 
 	msk = mptcp_sk(subflow->conn);
 	for (;;) {
-		u32 map_remaining;
-		size_t delta;
 		u64 ack_seq;
 		u64 old_ack;
 
@@ -849,6 +860,7 @@ 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 = MPTCP_SUBFLOW_DATA_AVAIL;
 			return true;
 		}
 
@@ -876,42 +888,18 @@ 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 = 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;
-		}
+		mptcp_subflow_discard_data(ssk, skb, old_ack - ack_seq);
 	}
 	return true;
 
@@ -922,13 +910,13 @@ static bool subflow_check_data_avail(struct sock *ssk)
 	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 +929,7 @@ 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,
@@ -996,8 +976,10 @@ 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 */
@@ -1056,8 +1038,7 @@ 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);
@@ -1101,7 +1082,7 @@ 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;
@@ -1112,7 +1093,7 @@ int __mptcp_subflow_connect(struct sock *sk, int ifindex,
 	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);

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
 

tools/testing/selftests/net/mptcp/simult_flows.sh

+#!/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