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>

7 files changed, 501 insertions, 181 deletions

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/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/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.c b/net/mptcp/protocol.c
index 683196225f91..ef0dd2f23482 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;
 };
 
@@ -110,64 +112,204 @@ static int __mptcp_socket_create(struct mptcp_sock *msk)
 	return 0;
 }
 
-static void __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk,
-			     struct sk_buff *skb,
-			     unsigned int offset, size_t copy_len)
+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)
+{
+	bool fragstolen;
+	int delta;
+
+	if (MPTCP_SKB_CB(from)->offset ||
+	    !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);
+	sk_mem_charge(sk, delta);
+	return true;
+}
+
+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 sk_buff *tail;
+	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;
+
+	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;
+	}
 
-	__skb_unlink(skb, &ssk->sk_receive_queue);
+	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);
+		msk->ooo_last_skb = skb;
+		goto end;
+	}
 
-	skb_ext_reset(skb);
-	skb_orphan(skb);
-	msk->ack_seq += copy_len;
+	/* 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)) {
+		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_OFOMERGE);
+		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_OFOQUEUETAIL);
+		return;
+	}
 
-	tail = skb_peek_tail(&sk->sk_receive_queue);
-	if (offset == 0 && tail) {
-		bool fragstolen;
-		int delta;
+	/* 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;
+	}
 
-		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);
+	/* 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);
+				MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_DUPDATA);
+				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);
+				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;
 	}
 
-	skb_set_owner_r(skb, sk);
-	__skb_queue_tail(&sk->sk_receive_queue, skb);
-	MPTCP_SKB_CB(skb)->offset = offset;
-}
+insert:
+	/* Insert segment into RB tree. */
+	rb_link_node(&skb->rbnode, parent, p);
+	rb_insert_color(&skb->rbnode, &msk->out_of_order_queue);
 
-static void mptcp_stop_timer(struct sock *sk)
-{
-	struct inet_connection_sock *icsk = inet_csk(sk);
+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);
+		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_DUPDATA);
+	}
+	/* If there is no skb after us, we are the last_skb ! */
+	if (!skb1)
+		msk->ooo_last_skb = skb;
 
-	sk_stop_timer(sk, &icsk->icsk_retransmit_timer);
-	mptcp_sk(sk)->timer_ival = 0;
+end:
+	skb_condense(skb);
+	skb_set_owner_r(skb, sk);
 }
 
-/* both sockets must be locked */
-static bool mptcp_subflow_dsn_valid(const struct mptcp_sock *msk,
-				    struct sock *ssk)
+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);
-	u64 dsn = mptcp_subflow_get_mapped_dsn(subflow);
+	struct sock *sk = (struct sock *)msk;
+	struct sk_buff *tail;
 
-	/* 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.
+	__skb_unlink(skb, &ssk->sk_receive_queue);
+
+	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
 	 */
-	if (likely(dsn == msk->ack_seq))
+	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;
+
+	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);
 		return true;
+	} else if (after64(MPTCP_SKB_CB(skb)->map_seq, msk->ack_seq)) {
+		mptcp_data_queue_ofo(msk, skb);
+		return false;
+	}
 
-	subflow->data_avail = 0;
-	return mptcp_subflow_data_available(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;
+}
+
+static void mptcp_stop_timer(struct sock *sk)
+{
+	struct inet_connection_sock *icsk = inet_csk(sk);
+
+	sk_stop_timer(sk, &icsk->icsk_retransmit_timer);
+	mptcp_sk(sk)->timer_ival = 0;
 }
 
 static void mptcp_check_data_fin_ack(struct sock *sk)
@@ -313,11 +455,7 @@ 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;
-		return false;
-	}
-
+	pr_debug("msk=%p ssk=%p", msk, ssk);
 	tp = tcp_sk(ssk);
 	do {
 		u32 map_remaining, offset;
@@ -355,9 +493,9 @@ 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;
@@ -376,20 +514,56 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk,
 		}
 	} while (more_data_avail);
 
-	*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);
+	*bytes += moved;
+	if (moved)
+		tcp_cleanup_rbuf(ssk, moved);
 
 	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);
+	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))
+			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);
+			MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_DUPDATA);
+			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 */
+			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);
+		}
+		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.
  */
@@ -405,8 +579,19 @@ 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);
 
@@ -415,9 +600,17 @@ 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 +631,8 @@ 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)
@@ -472,7 +666,7 @@ 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 +761,20 @@ 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 +817,15 @@ 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);
+		}
 	}
 }
 
@@ -801,60 +1016,128 @@ 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)
+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 *backup = NULL;
+	int i, nr_active = 0;
+	struct sock *ssk;
+	u64 ratio;
+	u32 pace;
 
-	sock_owned_by_me((const struct sock *)msk);
+	sock_owned_by_me((struct sock *)msk);
 
+	*sndbuf = 0;
 	if (!mptcp_ext_cache_refill(msk))
 		return NULL;
 
+	if (__mptcp_check_fallback(msk)) {
+		if (!msk->first)
+			return NULL;
+		*sndbuf = msk->first->sk_sndbuf;
+		return sk_stream_memory_free(msk->first) ? msk->first : NULL;
+	}
+
+	/* 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) {
-		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+		ssk =  mptcp_subflow_tcp_sock(subflow);
+		if (!mptcp_subflow_active(subflow))
+			continue;
 
-		if (!sk_stream_memory_free(ssk)) {
-			struct socket *sock = ssk->sk_socket;
+		nr_active += !subflow->backup;
+		*sndbuf = max(tcp_sk(ssk)->snd_wnd, *sndbuf);
+		if (!sk_stream_memory_free(subflow->tcp_sock))
+			continue;
 
-			if (sock)
-				mptcp_nospace(msk, sock);
+		pace = READ_ONCE(ssk->sk_pacing_rate);
+		if (!pace)
+			continue;
 
-			return NULL;
+		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;
 		}
+	}
 
-		if (subflow->backup) {
-			if (!backup)
-				backup = ssk;
+	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);
 
-			continue;
-		}
+	/* pick the best backup if no other subflow is active */
+	if (!nr_active)
+		send_info[0].ssk = send_info[1].ssk;
 
-		return 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 backup;
+	return NULL;
 }
 
-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)
@@ -864,6 +1147,7 @@ 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;
 
@@ -890,7 +1174,7 @@ 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)) {
@@ -907,19 +1191,25 @@ restart:
 				mptcp_reset_timer(sk);
 		}
 
+		mptcp_nospace(msk);
 		ret = sk_stream_wait_memory(sk, &timeo);
 		if (ret)
 			goto out;
 
 		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);
@@ -936,6 +1226,10 @@ 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);
@@ -945,7 +1239,6 @@ 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 +1286,9 @@ restart:
 			mptcp_reset_timer(sk);
 	}
 
-	ssk_check_wmem(msk, ssk);
 	release_sock(ssk);
 out:
+	ssk_check_wmem(msk);
 	release_sock(sk);
 	return copied ? : ret;
 }
@@ -1133,10 +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);
 			}
 		}
 	}
@@ -1152,6 +1449,11 @@ 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);
 
@@ -1163,7 +1465,11 @@ 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,
@@ -1259,6 +1565,9 @@ 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);
@@ -1309,9 +1618,15 @@ 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;
@@ -1472,6 +1787,7 @@ 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;
@@ -1505,7 +1821,7 @@ 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;
 }
@@ -1811,6 +2127,7 @@ 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);
@@ -2286,13 +2603,13 @@ 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);
 
 	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/protocol.h b/net/mptcp/protocol.h
index 60b27d44c184..493bd2c13bc6 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)
@@ -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);
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index e8cac2655c82..a2ae3087e24d 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"
 
@@ -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 @@ validate_seq:
 	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 @@ 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 +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);