11 files changed, 186 insertions, 179 deletions

diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c
index b21ff9be04c6..3240b72271a7 100644
--- a/net/mptcp/mib.c
+++ b/net/mptcp/mib.c
@@ -72,6 +72,7 @@ bool mptcp_mib_alloc(struct net *net)
 
 void mptcp_seq_show(struct seq_file *seq)
 {
+	unsigned long sum[ARRAY_SIZE(mptcp_snmp_list) - 1];
 	struct net *net = seq->private;
 	int i;
 
@@ -81,17 +82,13 @@ void mptcp_seq_show(struct seq_file *seq)
 
 	seq_puts(seq, "\nMPTcpExt:");
 
-	if (!net->mib.mptcp_statistics) {
-		for (i = 0; mptcp_snmp_list[i].name; i++)
-			seq_puts(seq, " 0");
-
-		seq_putc(seq, '\n');
-		return;
-	}
+	memset(sum, 0, sizeof(sum));
+	if (net->mib.mptcp_statistics)
+		snmp_get_cpu_field_batch(sum, mptcp_snmp_list,
+					 net->mib.mptcp_statistics);
 
 	for (i = 0; mptcp_snmp_list[i].name; i++)
-		seq_printf(seq, " %lu",
-			   snmp_fold_field(net->mib.mptcp_statistics,
-					   mptcp_snmp_list[i].entry));
+		seq_printf(seq, " %lu", sum[i]);
+
 	seq_putc(seq, '\n');
 }
diff --git a/net/mptcp/mptcp_diag.c b/net/mptcp/mptcp_diag.c
index fdf0c1f15a65..f44125dd6697 100644
--- a/net/mptcp/mptcp_diag.c
+++ b/net/mptcp/mptcp_diag.c
@@ -36,7 +36,7 @@ static int mptcp_diag_dump_one(struct netlink_callback *cb,
 	struct sock *sk;
 
 	net = sock_net(in_skb->sk);
-	msk = mptcp_token_get_sock(req->id.idiag_cookie[0]);
+	msk = mptcp_token_get_sock(net, req->id.idiag_cookie[0]);
 	if (!msk)
 		goto out_nosk;
 
diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index c41273cefc51..422f4acfb3e6 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -748,9 +748,7 @@ static bool mptcp_established_options_mp_prio(struct sock *sk,
 	/* can't send MP_PRIO with MPC, as they share the same option space:
 	 * 'backup'. Also it makes no sense at all
 	 */
-	if (!subflow->send_mp_prio ||
-	    ((OPTION_MPTCP_MPC_SYN | OPTION_MPTCP_MPC_SYNACK |
-	      OPTION_MPTCP_MPC_ACK) & opts->suboptions))
+	if (!subflow->send_mp_prio || (opts->suboptions & OPTIONS_MPTCP_MPC))
 		return false;
 
 	/* account for the trailing 'nop' option */
@@ -1019,11 +1017,9 @@ static void ack_update_msk(struct mptcp_sock *msk,
 	old_snd_una = msk->snd_una;
 	new_snd_una = mptcp_expand_seq(old_snd_una, mp_opt->data_ack, mp_opt->ack64);
 
-	/* ACK for data not even sent yet and even above recovery bound? Ignore.*/
-	if (unlikely(after64(new_snd_una, snd_nxt))) {
-		if (!msk->recovery || after64(new_snd_una, msk->recovery_snd_nxt))
-			new_snd_una = old_snd_una;
-	}
+	/* ACK for data not even sent yet? Ignore.*/
+	if (unlikely(after64(new_snd_una, snd_nxt)))
+		new_snd_una = old_snd_una;
 
 	new_wnd_end = new_snd_una + tcp_sk(ssk)->snd_wnd;
 
@@ -1329,8 +1325,7 @@ void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp,
 						   TCPOPT_NOP << 8 | TCPOPT_NOP, ptr);
 			}
 		}
-	} else if ((OPTION_MPTCP_MPC_SYN | OPTION_MPTCP_MPC_SYNACK |
-		    OPTION_MPTCP_MPC_ACK) & opts->suboptions) {
+	} else if (OPTIONS_MPTCP_MPC & opts->suboptions) {
 		u8 len, flag = MPTCP_CAP_HMAC_SHA256;
 
 		if (OPTION_MPTCP_MPC_SYN & opts->suboptions) {
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index c4f9a5ce3815..7b96be1e9f14 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -654,9 +654,9 @@ void mptcp_pm_nl_addr_send_ack(struct mptcp_sock *msk)
 	}
 }
 
-int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk,
-				 struct mptcp_addr_info *addr,
-				 u8 bkup)
+static int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk,
+					struct mptcp_addr_info *addr,
+					u8 bkup)
 {
 	struct mptcp_subflow_context *subflow;
 
@@ -1718,9 +1718,7 @@ static int mptcp_nl_cmd_set_flags(struct sk_buff *skb, struct genl_info *info)
 
 	list_for_each_entry(entry, &pernet->local_addr_list, list) {
 		if (addresses_equal(&entry->addr, &addr.addr, true)) {
-			ret = mptcp_nl_addr_backup(net, &entry->addr, bkup);
-			if (ret)
-				return ret;
+			mptcp_nl_addr_backup(net, &entry->addr, bkup);
 
 			if (bkup)
 				entry->flags |= MPTCP_PM_ADDR_FLAG_BACKUP;
@@ -2054,6 +2052,9 @@ static int __net_init pm_nl_init_net(struct net *net)
 	struct pm_nl_pernet *pernet = net_generic(net, pm_nl_pernet_id);
 
 	INIT_LIST_HEAD_RCU(&pernet->local_addr_list);
+
+	/* Cit. 2 subflows ought to be enough for anybody. */
+	pernet->subflows_max = 2;
 	pernet->next_id = 1;
 	pernet->stale_loss_cnt = 4;
 	spin_lock_init(&pernet->lock);
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 2602f1386160..cd6b11c9b54d 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -528,7 +528,6 @@ static bool mptcp_check_data_fin(struct sock *sk)
 
 		sk->sk_shutdown |= RCV_SHUTDOWN;
 		smp_mb__before_atomic(); /* SHUTDOWN must be visible first */
-		set_bit(MPTCP_DATA_READY, &msk->flags);
 
 		switch (sk->sk_state) {
 		case TCP_ESTABLISHED:
@@ -742,10 +741,9 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk)
 
 	/* Wake-up the reader only for in-sequence data */
 	mptcp_data_lock(sk);
-	if (move_skbs_to_msk(msk, ssk)) {
-		set_bit(MPTCP_DATA_READY, &msk->flags);
+	if (move_skbs_to_msk(msk, ssk))
 		sk->sk_data_ready(sk);
-	}
+
 	mptcp_data_unlock(sk);
 }
 
@@ -847,7 +845,6 @@ static void mptcp_check_for_eof(struct mptcp_sock *msk)
 		sk->sk_shutdown |= RCV_SHUTDOWN;
 
 		smp_mb__before_atomic(); /* SHUTDOWN must be visible first */
-		set_bit(MPTCP_DATA_READY, &msk->flags);
 		sk->sk_data_ready(sk);
 	}
 
@@ -956,9 +953,7 @@ static void __mptcp_update_wmem(struct sock *sk)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
 
-#ifdef CONFIG_LOCKDEP
-	WARN_ON_ONCE(!lockdep_is_held(&sk->sk_lock.slock));
-#endif
+	lockdep_assert_held_once(&sk->sk_lock.slock);
 
 	if (!msk->wmem_reserved)
 		return;
@@ -1107,7 +1102,8 @@ out:
 	if (cleaned && tcp_under_memory_pressure(sk))
 		__mptcp_mem_reclaim_partial(sk);
 
-	if (snd_una == READ_ONCE(msk->snd_nxt) && !msk->recovery) {
+	if (snd_una == READ_ONCE(msk->snd_nxt) &&
+	    snd_una == READ_ONCE(msk->write_seq)) {
 		if (mptcp_timer_pending(sk) && !mptcp_data_fin_enabled(msk))
 			mptcp_stop_timer(sk);
 	} else {
@@ -1117,9 +1113,8 @@ out:
 
 static void __mptcp_clean_una_wakeup(struct sock *sk)
 {
-#ifdef CONFIG_LOCKDEP
-	WARN_ON_ONCE(!lockdep_is_held(&sk->sk_lock.slock));
-#endif
+	lockdep_assert_held_once(&sk->sk_lock.slock);
+
 	__mptcp_clean_una(sk);
 	mptcp_write_space(sk);
 }
@@ -1224,6 +1219,7 @@ static struct sk_buff *__mptcp_do_alloc_tx_skb(struct sock *sk, gfp_t gfp)
 		if (likely(__mptcp_add_ext(skb, gfp))) {
 			skb_reserve(skb, MAX_TCP_HEADER);
 			skb->reserved_tailroom = skb->end - skb->tail;
+			INIT_LIST_HEAD(&skb->tcp_tsorted_anchor);
 			return skb;
 		}
 		__kfree_skb(skb);
@@ -1233,31 +1229,23 @@ static struct sk_buff *__mptcp_do_alloc_tx_skb(struct sock *sk, gfp_t gfp)
 	return NULL;
 }
 
-static bool __mptcp_alloc_tx_skb(struct sock *sk, struct sock *ssk, gfp_t gfp)
+static struct sk_buff *__mptcp_alloc_tx_skb(struct sock *sk, struct sock *ssk, gfp_t gfp)
 {
 	struct sk_buff *skb;
 
-	if (ssk->sk_tx_skb_cache) {
-		skb = ssk->sk_tx_skb_cache;
-		if (unlikely(!skb_ext_find(skb, SKB_EXT_MPTCP) &&
-			     !__mptcp_add_ext(skb, gfp)))
-			return false;
-		return true;
-	}
-
 	skb = __mptcp_do_alloc_tx_skb(sk, gfp);
 	if (!skb)
-		return false;
+		return NULL;
 
 	if (likely(sk_wmem_schedule(ssk, skb->truesize))) {
-		ssk->sk_tx_skb_cache = skb;
-		return true;
+		tcp_skb_entail(ssk, skb);
+		return skb;
 	}
 	kfree_skb(skb);
-	return false;
+	return NULL;
 }
 
-static bool mptcp_alloc_tx_skb(struct sock *sk, struct sock *ssk, bool data_lock_held)
+static struct sk_buff *mptcp_alloc_tx_skb(struct sock *sk, struct sock *ssk, bool data_lock_held)
 {
 	gfp_t gfp = data_lock_held ? GFP_ATOMIC : sk->sk_allocation;
 
@@ -1287,23 +1275,29 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
 			      struct mptcp_sendmsg_info *info)
 {
 	u64 data_seq = dfrag->data_seq + info->sent;
+	int offset = dfrag->offset + info->sent;
 	struct mptcp_sock *msk = mptcp_sk(sk);
 	bool zero_window_probe = false;
 	struct mptcp_ext *mpext = NULL;
-	struct sk_buff *skb, *tail;
-	bool must_collapse = false;
-	int size_bias = 0;
-	int avail_size;
-	size_t ret = 0;
+	bool can_coalesce = false;
+	bool reuse_skb = true;
+	struct sk_buff *skb;
+	size_t copy;
+	int i;
 
 	pr_debug("msk=%p ssk=%p sending dfrag at seq=%llu len=%u already sent=%u",
 		 msk, ssk, dfrag->data_seq, dfrag->data_len, info->sent);
 
+	if (WARN_ON_ONCE(info->sent > info->limit ||
+			 info->limit > dfrag->data_len))
+		return 0;
+
 	/* compute send limit */
 	info->mss_now = tcp_send_mss(ssk, &info->size_goal, info->flags);
-	avail_size = info->size_goal;
+	copy = info->size_goal;
+
 	skb = tcp_write_queue_tail(ssk);
-	if (skb) {
+	if (skb && copy > skb->len) {
 		/* Limit the write to the size available in the
 		 * current skb, if any, so that we create at most a new skb.
 		 * Explicitly tells TCP internals to avoid collapsing on later
@@ -1316,62 +1310,80 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
 			goto alloc_skb;
 		}
 
-		must_collapse = (info->size_goal - skb->len > 0) &&
-				(skb_shinfo(skb)->nr_frags < sysctl_max_skb_frags);
-		if (must_collapse) {
-			size_bias = skb->len;
-			avail_size = info->size_goal - skb->len;
+		i = skb_shinfo(skb)->nr_frags;
+		can_coalesce = skb_can_coalesce(skb, i, dfrag->page, offset);
+		if (!can_coalesce && i >= sysctl_max_skb_frags) {
+			tcp_mark_push(tcp_sk(ssk), skb);
+			goto alloc_skb;
 		}
-	}
 
+		copy -= skb->len;
+	} else {
 alloc_skb:
-	if (!must_collapse && !ssk->sk_tx_skb_cache &&
-	    !mptcp_alloc_tx_skb(sk, ssk, info->data_lock_held))
-		return 0;
+		skb = mptcp_alloc_tx_skb(sk, ssk, info->data_lock_held);
+		if (!skb)
+			return -ENOMEM;
+
+		i = skb_shinfo(skb)->nr_frags;
+		reuse_skb = false;
+		mpext = skb_ext_find(skb, SKB_EXT_MPTCP);
+	}
 
 	/* Zero window and all data acked? Probe. */
-	avail_size = mptcp_check_allowed_size(msk, data_seq, avail_size);
-	if (avail_size == 0) {
+	copy = mptcp_check_allowed_size(msk, data_seq, copy);
+	if (copy == 0) {
 		u64 snd_una = READ_ONCE(msk->snd_una);
 
-		if (skb || snd_una != msk->snd_nxt)
+		if (snd_una != msk->snd_nxt) {
+			tcp_remove_empty_skb(ssk, tcp_write_queue_tail(ssk));
 			return 0;
+		}
+
 		zero_window_probe = true;
 		data_seq = snd_una - 1;
-		avail_size = 1;
-	}
+		copy = 1;
 
-	if (WARN_ON_ONCE(info->sent > info->limit ||
-			 info->limit > dfrag->data_len))
-		return 0;
+		/* all mptcp-level data is acked, no skbs should be present into the
+		 * ssk write queue
+		 */
+		WARN_ON_ONCE(reuse_skb);
+	}
 
-	ret = info->limit - info->sent;
-	tail = tcp_build_frag(ssk, avail_size + size_bias, info->flags,
-			      dfrag->page, dfrag->offset + info->sent, &ret);
-	if (!tail) {
-		tcp_remove_empty_skb(sk, tcp_write_queue_tail(ssk));
+	copy = min_t(size_t, copy, info->limit - info->sent);
+	if (!sk_wmem_schedule(ssk, copy)) {
+		tcp_remove_empty_skb(ssk, tcp_write_queue_tail(ssk));
 		return -ENOMEM;
 	}
 
-	/* if the tail skb is still the cached one, collapsing really happened.
-	 */
-	if (skb == tail) {
-		TCP_SKB_CB(tail)->tcp_flags &= ~TCPHDR_PSH;
-		mpext->data_len += ret;
+	if (can_coalesce) {
+		skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy);
+	} else {
+		get_page(dfrag->page);
+		skb_fill_page_desc(skb, i, dfrag->page, offset, copy);
+	}
+
+	skb->len += copy;
+	skb->data_len += copy;
+	skb->truesize += copy;
+	sk_wmem_queued_add(ssk, copy);
+	sk_mem_charge(ssk, copy);
+	skb->ip_summed = CHECKSUM_PARTIAL;
+	WRITE_ONCE(tcp_sk(ssk)->write_seq, tcp_sk(ssk)->write_seq + copy);
+	TCP_SKB_CB(skb)->end_seq += copy;
+	tcp_skb_pcount_set(skb, 0);
+
+	/* on skb reuse we just need to update the DSS len */
+	if (reuse_skb) {
+		TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH;
+		mpext->data_len += copy;
 		WARN_ON_ONCE(zero_window_probe);
 		goto out;
 	}
 
-	mpext = skb_ext_find(tail, SKB_EXT_MPTCP);
-	if (WARN_ON_ONCE(!mpext)) {
-		/* should never reach here, stream corrupted */
-		return -EINVAL;
-	}
-
 	memset(mpext, 0, sizeof(*mpext));
 	mpext->data_seq = data_seq;
 	mpext->subflow_seq = mptcp_subflow_ctx(ssk)->rel_write_seq;
-	mpext->data_len = ret;
+	mpext->data_len = copy;
 	mpext->use_map = 1;
 	mpext->dsn64 = 1;
 
@@ -1380,18 +1392,18 @@ alloc_skb:
 		 mpext->dsn64);
 
 	if (zero_window_probe) {
-		mptcp_subflow_ctx(ssk)->rel_write_seq += ret;
+		mptcp_subflow_ctx(ssk)->rel_write_seq += copy;
 		mpext->frozen = 1;
 		if (READ_ONCE(msk->csum_enabled))
-			mptcp_update_data_checksum(tail, ret);
+			mptcp_update_data_checksum(skb, copy);
 		tcp_push_pending_frames(ssk);
 		return 0;
 	}
 out:
 	if (READ_ONCE(msk->csum_enabled))
-		mptcp_update_data_checksum(tail, ret);
-	mptcp_subflow_ctx(ssk)->rel_write_seq += ret;
-	return ret;
+		mptcp_update_data_checksum(skb, copy);
+	mptcp_subflow_ctx(ssk)->rel_write_seq += copy;
+	return copy;
 }
 
 #define MPTCP_SEND_BURST_SIZE		((1 << 16) - \
@@ -1508,6 +1520,38 @@ static void mptcp_push_release(struct sock *sk, struct sock *ssk,
 	release_sock(ssk);
 }
 
+static void mptcp_update_post_push(struct mptcp_sock *msk,
+				   struct mptcp_data_frag *dfrag,
+				   u32 sent)
+{
+	u64 snd_nxt_new = dfrag->data_seq;
+
+	dfrag->already_sent += sent;
+
+	msk->snd_burst -= sent;
+
+	snd_nxt_new += dfrag->already_sent;
+
+	/* snd_nxt_new can be smaller than snd_nxt in case mptcp
+	 * is recovering after a failover. In that event, this re-sends
+	 * old segments.
+	 *
+	 * Thus compute snd_nxt_new candidate based on
+	 * the dfrag->data_seq that was sent and the data
+	 * that has been handed to the subflow for transmission
+	 * and skip update in case it was old dfrag.
+	 */
+	if (likely(after64(snd_nxt_new, msk->snd_nxt)))
+		msk->snd_nxt = snd_nxt_new;
+}
+
+static void mptcp_check_and_set_pending(struct sock *sk)
+{
+	if (mptcp_send_head(sk) &&
+	    !test_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->flags))
+		set_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->flags);
+}
+
 void __mptcp_push_pending(struct sock *sk, unsigned int flags)
 {
 	struct sock *prev_ssk = NULL, *ssk = NULL;
@@ -1551,12 +1595,10 @@ void __mptcp_push_pending(struct sock *sk, unsigned int flags)
 			}
 
 			info.sent += ret;
-			dfrag->already_sent += ret;
-			msk->snd_nxt += ret;
-			msk->snd_burst -= ret;
-			msk->tx_pending_data -= ret;
 			copied += ret;
 			len -= ret;
+
+			mptcp_update_post_push(msk, dfrag, ret);
 		}
 		WRITE_ONCE(msk->first_pending, mptcp_send_next(sk));
 	}
@@ -1609,13 +1651,11 @@ static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk)
 				goto out;
 
 			info.sent += ret;
-			dfrag->already_sent += ret;
-			msk->snd_nxt += ret;
-			msk->snd_burst -= ret;
-			msk->tx_pending_data -= ret;
 			copied += ret;
 			len -= ret;
 			first = false;
+
+			mptcp_update_post_push(msk, dfrag, ret);
 		}
 		WRITE_ONCE(msk->first_pending, mptcp_send_next(sk));
 	}
@@ -1725,7 +1765,6 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		frag_truesize += psize;
 		pfrag->offset += frag_truesize;
 		WRITE_ONCE(msk->write_seq, msk->write_seq + psize);
-		msk->tx_pending_data += psize;
 
 		/* charge data on mptcp pending queue to the msk socket
 		 * Note: we charge such data both to sk and ssk
@@ -1759,21 +1798,6 @@ out:
 	return copied ? : ret;
 }
 
-static void mptcp_wait_data(struct sock *sk, long *timeo)
-{
-	DEFINE_WAIT_FUNC(wait, woken_wake_function);
-	struct mptcp_sock *msk = mptcp_sk(sk);
-
-	add_wait_queue(sk_sleep(sk), &wait);
-	sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
-
-	sk_wait_event(sk, timeo,
-		      test_bit(MPTCP_DATA_READY, &msk->flags), &wait);
-
-	sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
-	remove_wait_queue(sk_sleep(sk), &wait);
-}
-
 static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk,
 				struct msghdr *msg,
 				size_t len, int flags,
@@ -2077,19 +2101,7 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		}
 
 		pr_debug("block timeout %ld", timeo);
-		mptcp_wait_data(sk, &timeo);
-	}
-
-	if (skb_queue_empty_lockless(&sk->sk_receive_queue) &&
-	    skb_queue_empty(&msk->receive_queue)) {
-		/* entire backlog drained, clear DATA_READY. */
-		clear_bit(MPTCP_DATA_READY, &msk->flags);
-
-		/* .. race-breaker: ssk might have gotten new data
-		 * after last __mptcp_move_skbs() returned false.
-		 */
-		if (unlikely(__mptcp_move_skbs(msk)))
-			set_bit(MPTCP_DATA_READY, &msk->flags);
+		sk_wait_data(sk, &timeo, NULL);
 	}
 
 out_err:
@@ -2098,9 +2110,9 @@ out_err:
 			tcp_recv_timestamp(msg, sk, &tss);
 	}
 
-	pr_debug("msk=%p data_ready=%d rx queue empty=%d copied=%d",
-		 msk, test_bit(MPTCP_DATA_READY, &msk->flags),
-		 skb_queue_empty_lockless(&sk->sk_receive_queue), copied);
+	pr_debug("msk=%p rx queue empty=%d:%d copied=%d",
+		 msk, skb_queue_empty_lockless(&sk->sk_receive_queue),
+		 skb_queue_empty(&msk->receive_queue), copied);
 	if (!(flags & MSG_PEEK))
 		mptcp_rcv_space_adjust(msk, copied);
 
@@ -2213,15 +2225,11 @@ bool __mptcp_retransmit_pending_data(struct sock *sk)
 		return false;
 	}
 
-	/* will accept ack for reijected data before re-sending them */
-	if (!msk->recovery || after64(msk->snd_nxt, msk->recovery_snd_nxt))
-		msk->recovery_snd_nxt = msk->snd_nxt;
+	msk->recovery_snd_nxt = msk->snd_nxt;
 	msk->recovery = true;
 	mptcp_data_unlock(sk);
 
 	msk->first_pending = rtx_head;
-	msk->tx_pending_data += msk->snd_nxt - rtx_head->data_seq;
-	msk->snd_nxt = rtx_head->data_seq;
 	msk->snd_burst = 0;
 
 	/* be sure to clear the "sent status" on all re-injected fragments */
@@ -2368,7 +2376,6 @@ static void mptcp_check_fastclose(struct mptcp_sock *msk)
 	inet_sk_state_store(sk, TCP_CLOSE);
 	sk->sk_shutdown = SHUTDOWN_MASK;
 	smp_mb__before_atomic(); /* SHUTDOWN must be visible first */
-	set_bit(MPTCP_DATA_READY, &msk->flags);
 	set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags);
 
 	mptcp_close_wake_up(sk);
@@ -2384,6 +2391,9 @@ static void __mptcp_retrans(struct sock *sk)
 	int ret;
 
 	mptcp_clean_una_wakeup(sk);
+
+	/* first check ssk: need to kick "stale" logic */
+	ssk = mptcp_subflow_get_retrans(msk);
 	dfrag = mptcp_rtx_head(sk);
 	if (!dfrag) {
 		if (mptcp_data_fin_enabled(msk)) {
@@ -2396,10 +2406,12 @@ static void __mptcp_retrans(struct sock *sk)
 			goto reset_timer;
 		}
 
-		return;
+		if (!mptcp_send_head(sk))
+			return;
+
+		goto reset_timer;
 	}
 
-	ssk = mptcp_subflow_get_retrans(msk);
 	if (!ssk)
 		goto reset_timer;
 
@@ -2426,6 +2438,8 @@ static void __mptcp_retrans(struct sock *sk)
 	release_sock(ssk);
 
 reset_timer:
+	mptcp_check_and_set_pending(sk);
+
 	if (!mptcp_timer_pending(sk))
 		mptcp_reset_timer(sk);
 }
@@ -2492,7 +2506,6 @@ static int __mptcp_init_sock(struct sock *sk)
 	msk->first_pending = NULL;
 	msk->wmem_reserved = 0;
 	WRITE_ONCE(msk->rmem_released, 0);
-	msk->tx_pending_data = 0;
 	msk->timer_ival = TCP_RTO_MIN;
 
 	msk->first = NULL;
@@ -2735,7 +2748,7 @@ cleanup:
 	inet_csk(sk)->icsk_mtup.probe_timestamp = tcp_jiffies32;
 	mptcp_for_each_subflow(mptcp_sk(sk), subflow) {
 		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
-		bool slow = lock_sock_fast(ssk);
+		bool slow = lock_sock_fast_nested(ssk);
 
 		sock_orphan(ssk);
 		unlock_sock_fast(ssk, slow);
@@ -3385,8 +3398,14 @@ unlock_fail:
 
 static __poll_t mptcp_check_readable(struct mptcp_sock *msk)
 {
-	return test_bit(MPTCP_DATA_READY, &msk->flags) ? EPOLLIN | EPOLLRDNORM :
-	       0;
+	/* Concurrent splices from sk_receive_queue into receive_queue will
+	 * always show at least one non-empty queue when checked in this order.
+	 */
+	if (skb_queue_empty_lockless(&((struct sock *)msk)->sk_receive_queue) &&
+	    skb_queue_empty_lockless(&msk->receive_queue))
+		return 0;
+
+	return EPOLLIN | EPOLLRDNORM;
 }
 
 static __poll_t mptcp_check_writeable(struct mptcp_sock *msk)
@@ -3421,7 +3440,7 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock,
 	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);
+		return test_bit(MPTCP_DATA_READY, &msk->flags) ? EPOLLIN | EPOLLRDNORM : 0;
 
 	if (state != TCP_SYN_SENT && state != TCP_SYN_RECV) {
 		mask |= mptcp_check_readable(msk);
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index d3e6fd1615f1..284fdcec067e 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -254,7 +254,6 @@ struct mptcp_sock {
 	struct sk_buff  *ooo_last_skb;
 	struct rb_root  out_of_order_queue;
 	struct sk_buff_head receive_queue;
-	int		tx_pending_data;
 	struct list_head conn_list;
 	struct list_head rtx_queue;
 	struct mptcp_data_frag *first_pending;
@@ -709,7 +708,7 @@ int mptcp_token_new_connect(struct sock *sk);
 void mptcp_token_accept(struct mptcp_subflow_request_sock *r,
 			struct mptcp_sock *msk);
 bool mptcp_token_exists(u32 token);
-struct mptcp_sock *mptcp_token_get_sock(u32 token);
+struct mptcp_sock *mptcp_token_get_sock(struct net *net, u32 token);
 struct mptcp_sock *mptcp_token_iter_next(const struct net *net, long *s_slot,
 					 long *s_num);
 void mptcp_token_destroy(struct mptcp_sock *msk);
@@ -737,9 +736,6 @@ void mptcp_pm_nl_addr_send_ack(struct mptcp_sock *msk);
 void mptcp_pm_rm_addr_received(struct mptcp_sock *msk,
 			       const struct mptcp_rm_list *rm_list);
 void mptcp_pm_mp_prio_received(struct sock *sk, u8 bkup);
-int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk,
-				 struct mptcp_addr_info *addr,
-				 u8 bkup);
 void mptcp_pm_mp_fail_received(struct sock *sk, u64 fail_seq);
 void mptcp_pm_free_anno_list(struct mptcp_sock *msk);
 bool mptcp_pm_sport_in_anno_list(struct mptcp_sock *msk, const struct sock *sk);
diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c
index 8137cc3a4296..0f1e661c2032 100644
--- a/net/mptcp/sockopt.c
+++ b/net/mptcp/sockopt.c
@@ -861,6 +861,9 @@ static void mptcp_get_sub_addrs(const struct sock *sk, struct mptcp_subflow_addr
 	} else if (sk->sk_family == AF_INET6) {
 		const struct ipv6_pinfo *np = inet6_sk(sk);
 
+		if (WARN_ON_ONCE(!np))
+			return;
+
 		a->sin6_local.sin6_family = AF_INET6;
 		a->sin6_local.sin6_port = inet->inet_sport;
 
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 1de7ce883c37..6172f380dfb7 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -86,7 +86,7 @@ static struct mptcp_sock *subflow_token_join_request(struct request_sock *req)
 	struct mptcp_sock *msk;
 	int local_id;
 
-	msk = mptcp_token_get_sock(subflow_req->token);
+	msk = mptcp_token_get_sock(sock_net(req_to_sk(req)), subflow_req->token);
 	if (!msk) {
 		SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINNOTOKEN);
 		return NULL;
diff --git a/net/mptcp/syncookies.c b/net/mptcp/syncookies.c
index 37127781aee9..7f22526346a7 100644
--- a/net/mptcp/syncookies.c
+++ b/net/mptcp/syncookies.c
@@ -108,18 +108,12 @@ bool mptcp_token_join_cookie_init_state(struct mptcp_subflow_request_sock *subfl
 
 	e->valid = 0;
 
-	msk = mptcp_token_get_sock(e->token);
+	msk = mptcp_token_get_sock(net, e->token);
 	if (!msk) {
 		spin_unlock_bh(&join_entry_locks[i]);
 		return false;
 	}
 
-	/* If this fails, the token got re-used in the mean time by another
-	 * mptcp socket in a different netns, i.e. entry is outdated.
-	 */
-	if (!net_eq(sock_net((struct sock *)msk), net))
-		goto err_put;
-
 	subflow_req->remote_nonce = e->remote_nonce;
 	subflow_req->local_nonce = e->local_nonce;
 	subflow_req->backup = e->backup;
@@ -128,11 +122,6 @@ bool mptcp_token_join_cookie_init_state(struct mptcp_subflow_request_sock *subfl
 	subflow_req->msk = msk;
 	spin_unlock_bh(&join_entry_locks[i]);
 	return true;
-
-err_put:
-	spin_unlock_bh(&join_entry_locks[i]);
-	sock_put((struct sock *)msk);
-	return false;
 }
 
 void __init mptcp_join_cookie_init(void)
diff --git a/net/mptcp/token.c b/net/mptcp/token.c
index a98e554b034f..e581b341c5be 100644
--- a/net/mptcp/token.c
+++ b/net/mptcp/token.c
@@ -231,6 +231,7 @@ found:
 
 /**
  * mptcp_token_get_sock - retrieve mptcp connection sock using its token
+ * @net: restrict to this namespace
  * @token: token of the mptcp connection to retrieve
  *
  * This function returns the mptcp connection structure with the given token.
@@ -238,7 +239,7 @@ found:
  *
  * returns NULL if no connection with the given token value exists.
  */
-struct mptcp_sock *mptcp_token_get_sock(u32 token)
+struct mptcp_sock *mptcp_token_get_sock(struct net *net, u32 token)
 {
 	struct hlist_nulls_node *pos;
 	struct token_bucket *bucket;
@@ -251,11 +252,15 @@ struct mptcp_sock *mptcp_token_get_sock(u32 token)
 again:
 	sk_nulls_for_each_rcu(sk, pos, &bucket->msk_chain) {
 		msk = mptcp_sk(sk);
-		if (READ_ONCE(msk->token) != token)
+		if (READ_ONCE(msk->token) != token ||
+		    !net_eq(sock_net(sk), net))
 			continue;
+
 		if (!refcount_inc_not_zero(&sk->sk_refcnt))
 			goto not_found;
-		if (READ_ONCE(msk->token) != token) {
+
+		if (READ_ONCE(msk->token) != token ||
+		    !net_eq(sock_net(sk), net)) {
 			sock_put(sk);
 			goto again;
 		}
diff --git a/net/mptcp/token_test.c b/net/mptcp/token_test.c
index e1bd6f0a0676..5d984bec1cd8 100644
--- a/net/mptcp/token_test.c
+++ b/net/mptcp/token_test.c
@@ -11,6 +11,7 @@ static struct mptcp_subflow_request_sock *build_req_sock(struct kunit *test)
 			    GFP_USER);
 	KUNIT_EXPECT_NOT_ERR_OR_NULL(test, req);
 	mptcp_token_init_request((struct request_sock *)req);
+	sock_net_set((struct sock *)req, &init_net);
 	return req;
 }
 
@@ -22,7 +23,7 @@ static void mptcp_token_test_req_basic(struct kunit *test)
 	KUNIT_ASSERT_EQ(test, 0,
 			mptcp_token_new_request((struct request_sock *)req));
 	KUNIT_EXPECT_NE(test, 0, (int)req->token);
-	KUNIT_EXPECT_PTR_EQ(test, null_msk, mptcp_token_get_sock(req->token));
+	KUNIT_EXPECT_PTR_EQ(test, null_msk, mptcp_token_get_sock(&init_net, req->token));
 
 	/* cleanup */
 	mptcp_token_destroy_request((struct request_sock *)req);
@@ -55,6 +56,7 @@ static struct mptcp_sock *build_msk(struct kunit *test)
 	msk = kunit_kzalloc(test, sizeof(struct mptcp_sock), GFP_USER);
 	KUNIT_EXPECT_NOT_ERR_OR_NULL(test, msk);
 	refcount_set(&((struct sock *)msk)->sk_refcnt, 1);
+	sock_net_set((struct sock *)msk, &init_net);
 	return msk;
 }
 
@@ -74,11 +76,11 @@ static void mptcp_token_test_msk_basic(struct kunit *test)
 			mptcp_token_new_connect((struct sock *)icsk));
 	KUNIT_EXPECT_NE(test, 0, (int)ctx->token);
 	KUNIT_EXPECT_EQ(test, ctx->token, msk->token);
-	KUNIT_EXPECT_PTR_EQ(test, msk, mptcp_token_get_sock(ctx->token));
+	KUNIT_EXPECT_PTR_EQ(test, msk, mptcp_token_get_sock(&init_net, ctx->token));
 	KUNIT_EXPECT_EQ(test, 2, (int)refcount_read(&sk->sk_refcnt));
 
 	mptcp_token_destroy(msk);
-	KUNIT_EXPECT_PTR_EQ(test, null_msk, mptcp_token_get_sock(ctx->token));
+	KUNIT_EXPECT_PTR_EQ(test, null_msk, mptcp_token_get_sock(&init_net, ctx->token));
 }
 
 static void mptcp_token_test_accept(struct kunit *test)
@@ -90,11 +92,11 @@ static void mptcp_token_test_accept(struct kunit *test)
 			mptcp_token_new_request((struct request_sock *)req));
 	msk->token = req->token;
 	mptcp_token_accept(req, msk);
-	KUNIT_EXPECT_PTR_EQ(test, msk, mptcp_token_get_sock(msk->token));
+	KUNIT_EXPECT_PTR_EQ(test, msk, mptcp_token_get_sock(&init_net, msk->token));
 
 	/* this is now a no-op */
 	mptcp_token_destroy_request((struct request_sock *)req);
-	KUNIT_EXPECT_PTR_EQ(test, msk, mptcp_token_get_sock(msk->token));
+	KUNIT_EXPECT_PTR_EQ(test, msk, mptcp_token_get_sock(&init_net, msk->token));
 
 	/* cleanup */
 	mptcp_token_destroy(msk);
@@ -116,7 +118,7 @@ static void mptcp_token_test_destroyed(struct kunit *test)
 
 	/* simulate race on removal */
 	refcount_set(&sk->sk_refcnt, 0);
-	KUNIT_EXPECT_PTR_EQ(test, null_msk, mptcp_token_get_sock(msk->token));
+	KUNIT_EXPECT_PTR_EQ(test, null_msk, mptcp_token_get_sock(&init_net, msk->token));
 
 	/* cleanup */
 	mptcp_token_destroy(msk);