[PATCH net-next 0/5] mptcp: out-of-order queue pruning

[PATCH net-next 0/5] mptcp: out-of-order queue pruning

[Matthieu Baerts (NGI0)]

Under memory pressure, a pruning of the MPTCP-level OoO queue might be
required as last resort, to avoid too long recoveries, or even stalls.
Geliang and Gang managed to reproduce this behaviour, and Paolo
improved the situation thanks to the following patches:

- Patches 1-2: improve the MPTCP-level retransmission schema to make
  recoveries from memory pressure/after MPTCP-level drop significantly
  faster.

- Patches 2-3: make the admission check way stricter for incoming
  packets exceeding the memory limits, with some exceptions for fallback
  sockets.

- Patch 5: implement OoO queue pruning for MPTCP.

Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
---
Paolo Abeni (5):
      mptcp: move the retrans loop to a separate helper
      mptcp: let the retrans scheduler do its job
      mptcp: explicitly drop over memory limits
      mptcp: enforce hard limit on backlog flushing
      mptcp: implemented OoO queue pruning

 net/mptcp/mib.c      |   3 +
 net/mptcp/mib.h      |   3 +
 net/mptcp/options.c  |  28 +++++-
 net/mptcp/protocol.c | 251 +++++++++++++++++++++++++++++++++++++--------------
 4 files changed, 215 insertions(+), 70 deletions(-)
---
base-commit: 89d8006259b81dd25c962f6cc8d7ab268d6ea426
change-id: 20260724-net-next-mptcp-oooq-pruning-48566d10dbd0

Best regards,
--  
Matthieu Baerts (NGI0) <matttbe@kernel.org>

[PATCH net-next 1/5] mptcp: move the retrans loop to a separate helper

[Matthieu Baerts (NGI0)]

From: Paolo Abeni <pabeni@redhat.com>

This is a cleanup in order to make the next patch simpler.

No functional change intended.

Tested-by: Gang Yan <yangang@kylinos.cn>
Tested-by: Geliang Tang <geliang@kernel.org>
Acked-by: Geliang Tang <geliang@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
---
 net/mptcp/protocol.c | 74 ++++++++++++++++++++++++++++++----------------------
 1 file changed, 43 insertions(+), 31 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index ca644ec53eed..290d14e2fa5b 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -2785,41 +2785,14 @@ static void mptcp_check_fastclose(struct mptcp_sock *msk)
 	sk_error_report(sk);
 }
 
-static void __mptcp_retrans(struct sock *sk)
+/* Retransmit the specified data fragment on all the selected subflows. */
+static int __mptcp_push_retrans(struct sock *sk, struct mptcp_data_frag *dfrag)
 {
 	struct mptcp_sendmsg_info info = { .data_lock_held = true, };
 	struct mptcp_sock *msk = mptcp_sk(sk);
 	struct mptcp_subflow_context *subflow;
-	struct mptcp_data_frag *dfrag;
 	struct sock *ssk;
-	int ret, err;
-	u16 len = 0;
-
-	mptcp_clean_una_wakeup(sk);
-
-	/* first check ssk: need to kick "stale" logic */
-	err = mptcp_sched_get_retrans(msk);
-	dfrag = mptcp_rtx_head(sk);
-	if (!dfrag) {
-		if (mptcp_data_fin_enabled(msk)) {
-			struct inet_connection_sock *icsk = inet_csk(sk);
-
-			WRITE_ONCE(icsk->icsk_retransmits,
-				   icsk->icsk_retransmits + 1);
-			mptcp_set_datafin_timeout(sk);
-			mptcp_send_ack(msk);
-
-			goto reset_timer;
-		}
-
-		if (!mptcp_send_head(sk))
-			goto clear_scheduled;
-
-		goto reset_timer;
-	}
-
-	if (err)
-		goto reset_timer;
+	int ret, len = 0;
 
 	mptcp_for_each_subflow(msk, subflow) {
 		if (READ_ONCE(subflow->scheduled)) {
@@ -2847,7 +2820,7 @@ static void __mptcp_retrans(struct sock *sk)
 			    !msk->allow_subflows) {
 				spin_unlock_bh(&msk->fallback_lock);
 				release_sock(ssk);
-				goto clear_scheduled;
+				return -1;
 			}
 
 			while (info.sent < info.limit) {
@@ -2870,6 +2843,45 @@ static void __mptcp_retrans(struct sock *sk)
 			release_sock(ssk);
 		}
 	}
+	return len;
+}
+
+static void __mptcp_retrans(struct sock *sk)
+{
+	struct mptcp_sock *msk = mptcp_sk(sk);
+	struct mptcp_subflow_context *subflow;
+	struct mptcp_data_frag *dfrag;
+	int err, len;
+
+	mptcp_clean_una_wakeup(sk);
+
+	/* first check ssk: need to kick "stale" logic */
+	err = mptcp_sched_get_retrans(msk);
+	dfrag = mptcp_rtx_head(sk);
+	if (!dfrag) {
+		if (mptcp_data_fin_enabled(msk)) {
+			struct inet_connection_sock *icsk = inet_csk(sk);
+
+			WRITE_ONCE(icsk->icsk_retransmits,
+				   icsk->icsk_retransmits + 1);
+			mptcp_set_datafin_timeout(sk);
+			mptcp_send_ack(msk);
+
+			goto reset_timer;
+		}
+
+		if (!mptcp_send_head(sk))
+			goto clear_scheduled;
+
+		goto reset_timer;
+	}
+
+	if (err)
+		goto reset_timer;
+
+	len = __mptcp_push_retrans(sk, dfrag);
+	if (len < 0)
+		goto clear_scheduled;
 
 	msk->bytes_retrans += len;
 	dfrag->already_sent = max(dfrag->already_sent, len);

-- 
2.53.0

[PATCH net-next 2/5] mptcp: let the retrans scheduler do its job

[Matthieu Baerts (NGI0)]

From: Paolo Abeni <pabeni@redhat.com>

Currently the MPTCP core enforces that when MPTCP-level retrans timer
fires, at most a single dfrag is retransmitted. In some corner-cases, it
may be necessary to retransmit multiple dfrags, and the MPTCP socket
will need to wait multiple retrans timeout to accomplish that.

Remove the mentioned constraint, allowing to transmit multiple dfrags
per retrans period, as long as the scheduler keeps selecting subflows
for retransmissions and pending data is available in the rtx queue.
The default scheduler will transmit a dfrag per available subflow.

Tested-by: Gang Yan <yangang@kylinos.cn>
Tested-by: Geliang Tang <geliang@kernel.org>
Acked-by: Geliang Tang <geliang@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
---
 net/mptcp/protocol.c | 119 +++++++++++++++++++++++++++++++++++++--------------
 1 file changed, 87 insertions(+), 32 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 290d14e2fa5b..72b1fa3ca71c 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1136,13 +1136,6 @@ static void __mptcp_clean_una_wakeup(struct sock *sk)
 	mptcp_write_space(sk);
 }
 
-static void mptcp_clean_una_wakeup(struct sock *sk)
-{
-	mptcp_data_lock(sk);
-	__mptcp_clean_una_wakeup(sk);
-	mptcp_data_unlock(sk);
-}
-
 static void mptcp_enter_memory_pressure(struct sock *sk)
 {
 	struct mptcp_subflow_context *subflow;
@@ -2785,8 +2778,12 @@ static void mptcp_check_fastclose(struct mptcp_sock *msk)
 	sk_error_report(sk);
 }
 
-/* Retransmit the specified data fragment on all the selected subflows. */
-static int __mptcp_push_retrans(struct sock *sk, struct mptcp_data_frag *dfrag)
+/*
+ * Retransmit the specified data fragment on all the selected subflows,
+ * starting from the specified sequence
+ */
+static int __mptcp_push_retrans(struct sock *sk, struct mptcp_data_frag *dfrag,
+				u64 sent_seq)
 {
 	struct mptcp_sendmsg_info info = { .data_lock_held = true, };
 	struct mptcp_sock *msk = mptcp_sk(sk);
@@ -2796,6 +2793,7 @@ static int __mptcp_push_retrans(struct sock *sk, struct mptcp_data_frag *dfrag)
 
 	mptcp_for_each_subflow(msk, subflow) {
 		if (READ_ONCE(subflow->scheduled)) {
+			u16 offset = sent_seq - dfrag->data_seq;
 			u16 copied = 0;
 
 			mptcp_subflow_set_scheduled(subflow, false);
@@ -2805,7 +2803,7 @@ static int __mptcp_push_retrans(struct sock *sk, struct mptcp_data_frag *dfrag)
 			lock_sock(ssk);
 
 			/* limit retransmission to the bytes already sent on some subflows */
-			info.sent = 0;
+			info.sent = offset;
 			info.limit = READ_ONCE(msk->csum_enabled) ? dfrag->data_len :
 								    dfrag->already_sent;
 
@@ -2851,14 +2849,88 @@ static void __mptcp_retrans(struct sock *sk)
 	struct mptcp_sock *msk = mptcp_sk(sk);
 	struct mptcp_subflow_context *subflow;
 	struct mptcp_data_frag *dfrag;
+	bool need_retrans;
+	u64 retrans_seq;
 	int err, len;
 
-	mptcp_clean_una_wakeup(sk);
-
-	/* first check ssk: need to kick "stale" logic */
-	err = mptcp_sched_get_retrans(msk);
+	mptcp_data_lock(sk);
+	__mptcp_clean_una_wakeup(sk);
+	retrans_seq = msk->snd_una;
 	dfrag = mptcp_rtx_head(sk);
-	if (!dfrag) {
+	need_retrans = !!dfrag;
+	mptcp_data_unlock(sk);
+	if (!dfrag)
+		goto check_data_fin;
+
+	for (;;) {
+		bool already_retrans;
+		u64 sent_seq;
+
+		/* The default scheduler will kick "stale" logic, that in
+		 * turn can process incoming acks and clean the RTX queue;
+		 * ensure that the current dfrag will still be around
+		 * afterwards.
+		 */
+		get_page(dfrag->page);
+		err = mptcp_sched_get_retrans(msk);
+		if (err) {
+			put_page(dfrag->page);
+			break;
+		}
+
+		/* Incoming acks can have moved retrans sequence after
+		 * the current dfrag, if so try to start again from RTX head.
+		 */
+		mptcp_data_lock(sk);
+		already_retrans = !before64(msk->snd_una, dfrag->data_seq +
+					    dfrag->already_sent);
+		put_page(dfrag->page);
+		if (already_retrans) {
+			__mptcp_clean_una_wakeup(sk);
+			retrans_seq = msk->snd_una;
+			dfrag = mptcp_rtx_head(sk);
+			need_retrans = !!dfrag;
+		} else if (after64(msk->snd_una, retrans_seq)) {
+			retrans_seq = msk->snd_una;
+		}
+		mptcp_data_unlock(sk);
+
+		/* `already_sent` can be 0 for `dfrag` belonging to the RTX
+		 *  queue due to __mptcp_retransmit_pending_data().
+		 */
+		if (!dfrag || !dfrag->already_sent)
+			break;
+
+		/* Can fail only in case of fallback. */
+		len = __mptcp_push_retrans(sk, dfrag, retrans_seq);
+		if (len < 0)
+			goto clear_scheduled;
+
+		retrans_seq += len;
+		msk->bytes_retrans += len;
+		dfrag->already_sent = max_t(u16, dfrag->already_sent,
+					    retrans_seq - dfrag->data_seq);
+
+		/* With csum enabled retransmission can send new data. */
+		sent_seq = dfrag->already_sent + dfrag->data_seq;
+		if (after64(sent_seq, msk->snd_nxt))
+			WRITE_ONCE(msk->snd_nxt, sent_seq);
+
+		/* Attempt the next fragment only if the current one is
+		 * completely retransmitted.
+		 */
+		if (before64(retrans_seq, dfrag->data_seq + dfrag->data_len))
+			break;
+
+		dfrag = list_is_last(&dfrag->list, &msk->rtx_queue) ?
+				NULL : list_next_entry(dfrag, list);
+		if (!dfrag)
+			break;
+	}
+
+	/* Attempt data-fin retransmission only when the RTX queue is empty. */
+	if (!need_retrans) {
+check_data_fin:
 		if (mptcp_data_fin_enabled(msk)) {
 			struct inet_connection_sock *icsk = inet_csk(sk);
 
@@ -2866,30 +2938,13 @@ static void __mptcp_retrans(struct sock *sk)
 				   icsk->icsk_retransmits + 1);
 			mptcp_set_datafin_timeout(sk);
 			mptcp_send_ack(msk);
-
 			goto reset_timer;
 		}
 
 		if (!mptcp_send_head(sk))
 			goto clear_scheduled;
-
-		goto reset_timer;
 	}
 
-	if (err)
-		goto reset_timer;
-
-	len = __mptcp_push_retrans(sk, dfrag);
-	if (len < 0)
-		goto clear_scheduled;
-
-	msk->bytes_retrans += len;
-	dfrag->already_sent = max(dfrag->already_sent, len);
-
-	/* With csum enabled retransmission can send new data. */
-	if (after64(dfrag->already_sent + dfrag->data_seq, msk->snd_nxt))
-		WRITE_ONCE(msk->snd_nxt, dfrag->already_sent + dfrag->data_seq);
-
 reset_timer:
 	mptcp_check_and_set_pending(sk);
 

-- 
2.53.0

[PATCH net-next 3/5] mptcp: explicitly drop over memory limits

[Matthieu Baerts (NGI0)]

From: Paolo Abeni <pabeni@redhat.com>

Currently the enforcement of the rcvbuf constraint is implemented
when moving the skbs into the msk receive or OoO queue, keeping the
incoming skbs in the subflow queue when over limits.

Under significant memory pressure the above can cause permanent data
transfer stalls, as the skb needed to make forward progress can be
stuck in a subflow queue.

Over memory limits, drop the incoming skb, relying on MPTCP-level
retransmissions.

Note that fallback socket must perform the limit before the skb reaches
the subflow-level queue, as dropping an in-sequence already acked skb
would break the stream.

This is not a complete fix for the stall issue, as the drop strategy
needs refinements that will come in the next patches.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
---
 net/mptcp/mib.c      |  2 ++
 net/mptcp/mib.h      |  2 ++
 net/mptcp/options.c  | 28 +++++++++++++++++++++++++---
 net/mptcp/protocol.c | 31 +++++++++++++++++++++++--------
 4 files changed, 52 insertions(+), 11 deletions(-)

diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c
index f23fda0c55a7..ef65e2df709f 100644
--- a/net/mptcp/mib.c
+++ b/net/mptcp/mib.c
@@ -85,6 +85,8 @@ static const struct snmp_mib mptcp_snmp_list[] = {
 	SNMP_MIB_ITEM("SimultConnectFallback", MPTCP_MIB_SIMULTCONNFALLBACK),
 	SNMP_MIB_ITEM("FallbackFailed", MPTCP_MIB_FALLBACKFAILED),
 	SNMP_MIB_ITEM("WinProbe", MPTCP_MIB_WINPROBE),
+	SNMP_MIB_ITEM("BacklogDrop", MPTCP_MIB_BACKLOGDROP),
+	SNMP_MIB_ITEM("RcvPruned", MPTCP_MIB_RCVPRUNED),
 };
 
 /* mptcp_mib_alloc - allocate percpu mib counters
diff --git a/net/mptcp/mib.h b/net/mptcp/mib.h
index 812218b5ed2b..c84eb853d499 100644
--- a/net/mptcp/mib.h
+++ b/net/mptcp/mib.h
@@ -88,6 +88,8 @@ enum linux_mptcp_mib_field {
 	MPTCP_MIB_SIMULTCONNFALLBACK,	/* Simultaneous connect */
 	MPTCP_MIB_FALLBACKFAILED,	/* Can't fallback due to msk status */
 	MPTCP_MIB_WINPROBE,		/* MPTCP-level zero window probe */
+	MPTCP_MIB_BACKLOGDROP,		/* Backlog over memory limit */
+	MPTCP_MIB_RCVPRUNED,		/* Dropped due to memory constrains */
 	__MPTCP_MIB_MAX
 };
 
diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index c664023d37ba..7b954ef78672 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -1127,8 +1127,30 @@ static bool add_addr_hmac_valid(struct mptcp_sock *msk,
 	return hmac == mp_opt->ahmac;
 }
 
-/* Return false in case of error (or subflow has been reset),
- * else return true.
+static bool mptcp_over_limit(struct sock *sk, struct sock *ssk,
+			     const struct sk_buff *skb)
+{
+	struct mptcp_sock *msk = mptcp_sk(sk);
+	u64 mem = sk_rmem_alloc_get(sk);
+
+	mem += READ_ONCE(msk->backlog_len);
+	if (likely(mem <= READ_ONCE(sk->sk_rcvbuf)))
+		return false;
+
+	/* Avoid silently dropping pure acks, fin or zero win probes. */
+	if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq ||
+	    TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN ||
+	    !after(TCP_SKB_CB(skb)->end_seq, tcp_sk(ssk)->rcv_nxt))
+		return false;
+
+	/* Dropped due to memory constraints, schedule an ack. */
+	inet_csk(ssk)->icsk_ack.pending |= ICSK_ACK_NOMEM | ICSK_ACK_NOW;
+	inet_csk_schedule_ack(ssk);
+	return true;
+}
+
+/* Return false when the caller must drop the packet, i.e. in case of error,
+ * subflow has been reset, or over memory limits.
  */
 bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
 {
@@ -1154,7 +1176,7 @@ bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
 
 		__mptcp_data_acked(subflow->conn);
 		mptcp_data_unlock(subflow->conn);
-		return true;
+		return !mptcp_over_limit(subflow->conn, sk, skb);
 	}
 
 	mptcp_get_options(skb, &mp_opt);
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 72b1fa3ca71c..5f7d8340a3d9 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -381,6 +381,16 @@ static bool __mptcp_move_skb(struct sock *sk, struct sk_buff *skb)
 
 	mptcp_borrow_fwdmem(sk, skb);
 
+	/* Can't drop packets for fallback socket this late, or the stream
+	 * will break.
+	 */
+	if (unlikely(sk_rmem_alloc_get(sk) > READ_ONCE(sk->sk_rcvbuf)) &&
+	    !__mptcp_check_fallback(msk)) {
+		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RCVPRUNED);
+		mptcp_drop(sk, skb);
+		return false;
+	}
+
 	if (MPTCP_SKB_CB(skb)->map_seq == msk->ack_seq) {
 		/* in sequence */
 		msk->bytes_received += copy_len;
@@ -675,6 +685,7 @@ static void __mptcp_add_backlog(struct sock *sk,
 	struct sk_buff *tail = NULL;
 	struct sock *ssk = skb->sk;
 	bool fragstolen;
+	u64 limit;
 	int delta;
 
 	if (unlikely(sk->sk_state == TCP_CLOSE)) {
@@ -682,6 +693,16 @@ static void __mptcp_add_backlog(struct sock *sk,
 		return;
 	}
 
+	/* Similar additional allowance as plain TCP. */
+	limit = READ_ONCE(sk->sk_rcvbuf);
+	limit += (limit >> 1) + 64 * 1024;
+	limit = min_t(u64, limit, UINT_MAX);
+	if (msk->backlog_len > limit && !__mptcp_check_fallback(msk)) {
+		__MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_BACKLOGDROP);
+		kfree_skb_reason(skb, SKB_DROP_REASON_SOCKET_BACKLOG);
+		return;
+	}
+
 	/* Try to coalesce with the last skb in our backlog */
 	if (!list_empty(&msk->backlog_list))
 		tail = list_last_entry(&msk->backlog_list, struct sk_buff, list);
@@ -753,7 +774,7 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk,
 
 			mptcp_init_skb(ssk, skb, offset, len);
 
-			if (own_msk && sk_rmem_alloc_get(sk) < sk->sk_rcvbuf) {
+			if (own_msk) {
 				mptcp_subflow_lend_fwdmem(subflow, skb);
 				ret |= __mptcp_move_skb(sk, skb);
 			} else {
@@ -2204,10 +2225,6 @@ static bool __mptcp_move_skbs(struct sock *sk, struct list_head *skbs, u32 *delt
 
 	*delta = 0;
 	while (1) {
-		/* If the msk recvbuf is full stop, don't drop */
-		if (sk_rmem_alloc_get(sk) > sk->sk_rcvbuf)
-			break;
-
 		prefetch(skb->next);
 		list_del(&skb->list);
 		*delta += skb->truesize;
@@ -2235,9 +2252,7 @@ static bool mptcp_can_spool_backlog(struct sock *sk, struct list_head *skbs)
 	DEBUG_NET_WARN_ON_ONCE(msk->backlog_unaccounted && sk->sk_socket &&
 			       mem_cgroup_from_sk(sk));
 
-	/* Don't spool the backlog if the rcvbuf is full. */
-	if (list_empty(&msk->backlog_list) ||
-	    sk_rmem_alloc_get(sk) > sk->sk_rcvbuf)
+	if (list_empty(&msk->backlog_list))
 		return false;
 
 	INIT_LIST_HEAD(skbs);

-- 
2.53.0

[PATCH net-next 4/5] mptcp: enforce hard limit on backlog flushing

[Matthieu Baerts (NGI0)]

From: Paolo Abeni <pabeni@redhat.com>

Currently a wild producer could keep the backlog flushing operation
spinning for an unbound time.

Since the previous patch, the amount of data present in the backlog is
hard-limited. Move the backlog len update at the end of the flush loop to
prevent it spinning forever.

Also, no need to splice back the remaining skbs list into the backlog, as
such list is always empty after each backlog processing loop.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
---
 net/mptcp/protocol.c | 21 ++++++---------------
 1 file changed, 6 insertions(+), 15 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 5f7d8340a3d9..7f257419c5ea 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -2223,7 +2223,6 @@ static bool __mptcp_move_skbs(struct sock *sk, struct list_head *skbs, u32 *delt
 	struct mptcp_sock *msk = mptcp_sk(sk);
 	bool moved = false;
 
-	*delta = 0;
 	while (1) {
 		prefetch(skb->next);
 		list_del(&skb->list);
@@ -2260,20 +2259,12 @@ static bool mptcp_can_spool_backlog(struct sock *sk, struct list_head *skbs)
 	return true;
 }
 
-static void mptcp_backlog_spooled(struct sock *sk, u32 moved,
-				  struct list_head *skbs)
-{
-	struct mptcp_sock *msk = mptcp_sk(sk);
-
-	WRITE_ONCE(msk->backlog_len, msk->backlog_len - moved);
-	list_splice(skbs, &msk->backlog_list);
-}
-
 static bool mptcp_move_skbs(struct sock *sk)
 {
+	struct mptcp_sock *msk = mptcp_sk(sk);
 	struct list_head skbs;
 	bool enqueued = false;
-	u32 moved;
+	u32 moved = 0;
 
 	mptcp_data_lock(sk);
 	while (mptcp_can_spool_backlog(sk, &skbs)) {
@@ -2281,8 +2272,8 @@ static bool mptcp_move_skbs(struct sock *sk)
 		enqueued |= __mptcp_move_skbs(sk, &skbs, &moved);
 
 		mptcp_data_lock(sk);
-		mptcp_backlog_spooled(sk, moved, &skbs);
 	}
+	WRITE_ONCE(msk->backlog_len, msk->backlog_len - moved);
 	mptcp_data_unlock(sk);
 
 	if (enqueued && mptcp_epollin_ready(sk))
@@ -3752,12 +3743,12 @@ static void mptcp_release_cb(struct sock *sk)
 	__must_hold(&sk->sk_lock.slock)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
+	u32 moved = 0;
 
 	for (;;) {
 		unsigned long flags = (msk->cb_flags & MPTCP_FLAGS_PROCESS_CTX_NEED);
 		struct list_head join_list, skbs;
 		bool spool_bl;
-		u32 moved;
 
 		spool_bl = mptcp_can_spool_backlog(sk, &skbs);
 		if (!flags && !spool_bl)
@@ -3790,9 +3781,9 @@ static void mptcp_release_cb(struct sock *sk)
 
 		cond_resched();
 		spin_lock_bh(&sk->sk_lock.slock);
-		if (spool_bl)
-			mptcp_backlog_spooled(sk, moved, &skbs);
 	}
+	if (moved)
+		WRITE_ONCE(msk->backlog_len, msk->backlog_len - moved);
 
 	if (__test_and_clear_bit(MPTCP_CLEAN_UNA, &msk->cb_flags))
 		__mptcp_clean_una_wakeup(sk);

-- 
2.53.0

[PATCH net-next 5/5] mptcp: implemented OoO queue pruning

[Matthieu Baerts (NGI0)]

From: Paolo Abeni <pabeni@redhat.com>

When moving incoming skbs in the msk receive queue and the latter
is above limits, prune it as needed quite alike what TCP is doing
at the subflow level. The main difference relies in the stop condition:
since MPTCP does not perform collapsing, it's better off dropping the
bare minimum to fit the (newer) incoming packet.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Tested-by: Gang Yan <yangang@kylinos.cn>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
---
 net/mptcp/mib.c      |  1 +
 net/mptcp/mib.h      |  1 +
 net/mptcp/protocol.c | 46 +++++++++++++++++++++++++++++++++++++++++++++-
 3 files changed, 47 insertions(+), 1 deletion(-)

diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c
index ef65e2df709f..d9bd4f4afcc0 100644
--- a/net/mptcp/mib.c
+++ b/net/mptcp/mib.c
@@ -87,6 +87,7 @@ static const struct snmp_mib mptcp_snmp_list[] = {
 	SNMP_MIB_ITEM("WinProbe", MPTCP_MIB_WINPROBE),
 	SNMP_MIB_ITEM("BacklogDrop", MPTCP_MIB_BACKLOGDROP),
 	SNMP_MIB_ITEM("RcvPruned", MPTCP_MIB_RCVPRUNED),
+	SNMP_MIB_ITEM("OfoPruned", MPTCP_MIB_OFO_PRUNED),
 };
 
 /* mptcp_mib_alloc - allocate percpu mib counters
diff --git a/net/mptcp/mib.h b/net/mptcp/mib.h
index c84eb853d499..18f35f7e0a2d 100644
--- a/net/mptcp/mib.h
+++ b/net/mptcp/mib.h
@@ -90,6 +90,7 @@ enum linux_mptcp_mib_field {
 	MPTCP_MIB_WINPROBE,		/* MPTCP-level zero window probe */
 	MPTCP_MIB_BACKLOGDROP,		/* Backlog over memory limit */
 	MPTCP_MIB_RCVPRUNED,		/* Dropped due to memory constrains */
+	MPTCP_MIB_OFO_PRUNED,		/* MPTCP-level OoO queue pruned */
 	__MPTCP_MIB_MAX
 };
 
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 7f257419c5ea..5cf44eab76f1 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -373,6 +373,49 @@ static void mptcp_init_skb(struct sock *ssk, struct sk_buff *skb, int offset,
 	skb_dst_drop(skb);
 }
 
+/* "Inspired" from the TCP version; main difference: stop as soon as the MPTCP
+ * socket is under memory limit.
+ */
+static bool mptcp_prune_ofo_queue(struct sock *sk, u64 seq)
+{
+	struct mptcp_sock *msk = mptcp_sk(sk);
+	struct rb_node *node, *prev;
+	bool pruned = false;
+	u64 mem;
+
+	if (RB_EMPTY_ROOT(&msk->out_of_order_queue))
+		goto out;
+
+	node = &msk->ooo_last_skb->rbnode;
+
+	do {
+		struct sk_buff *skb = rb_to_skb(node);
+
+		/* Stop pruning if the incoming skb would land in OoO tail. */
+		if (after64(seq, MPTCP_SKB_CB(skb)->map_seq))
+			break;
+
+		pruned = true;
+		prev = rb_prev(node);
+		rb_erase(node, &msk->out_of_order_queue);
+		mptcp_drop(sk, skb);
+		msk->ooo_last_skb = rb_to_skb(prev);
+
+		mem = (unsigned int)sk_rmem_alloc_get(sk);
+		if (mem <= sk->sk_rcvbuf)
+			break;
+
+		node = prev;
+	} while (node);
+
+	if (pruned)
+		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_OFO_PRUNED);
+
+out:
+	mem = (unsigned int)sk_rmem_alloc_get(sk);
+	return mem <= sk->sk_rcvbuf;
+}
+
 static bool __mptcp_move_skb(struct sock *sk, struct sk_buff *skb)
 {
 	u64 copy_len = MPTCP_SKB_CB(skb)->end_seq - MPTCP_SKB_CB(skb)->map_seq;
@@ -385,7 +428,8 @@ static bool __mptcp_move_skb(struct sock *sk, struct sk_buff *skb)
 	 * will break.
 	 */
 	if (unlikely(sk_rmem_alloc_get(sk) > READ_ONCE(sk->sk_rcvbuf)) &&
-	    !__mptcp_check_fallback(msk)) {
+	    !__mptcp_check_fallback(msk) &&
+	    !mptcp_prune_ofo_queue(sk, MPTCP_SKB_CB(skb)->map_seq)) {
 		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RCVPRUNED);
 		mptcp_drop(sk, skb);
 		return false;

-- 
2.53.0

Re: [PATCH net-next 3/5] mptcp: explicitly drop over memory limits

[Paolo Abeni]

On 7/24/26 4:02 PM, Matthieu Baerts (NGI0) wrote:
> From: Paolo Abeni <pabeni@redhat.com>
> 
> Currently the enforcement of the rcvbuf constraint is implemented
> when moving the skbs into the msk receive or OoO queue, keeping the
> incoming skbs in the subflow queue when over limits.
> 
> Under significant memory pressure the above can cause permanent data
> transfer stalls, as the skb needed to make forward progress can be
> stuck in a subflow queue.
> 
> Over memory limits, drop the incoming skb, relying on MPTCP-level
> retransmissions.
> 
> Note that fallback socket must perform the limit before the skb reaches
> the subflow-level queue, as dropping an in-sequence already acked skb
> would break the stream.
> 
> This is not a complete fix for the stall issue, as the drop strategy
> needs refinements that will come in the next patches.
> 
> Signed-off-by: Paolo Abeni <pabeni@redhat.com>
> Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
> Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
> ---
>  net/mptcp/mib.c      |  2 ++
>  net/mptcp/mib.h      |  2 ++
>  net/mptcp/options.c  | 28 +++++++++++++++++++++++++---
>  net/mptcp/protocol.c | 31 +++++++++++++++++++++++--------
>  4 files changed, 52 insertions(+), 11 deletions(-)
> 
> diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c
> index f23fda0c55a7..ef65e2df709f 100644
> --- a/net/mptcp/mib.c
> +++ b/net/mptcp/mib.c
> @@ -85,6 +85,8 @@ static const struct snmp_mib mptcp_snmp_list[] = {
>  	SNMP_MIB_ITEM("SimultConnectFallback", MPTCP_MIB_SIMULTCONNFALLBACK),
>  	SNMP_MIB_ITEM("FallbackFailed", MPTCP_MIB_FALLBACKFAILED),
>  	SNMP_MIB_ITEM("WinProbe", MPTCP_MIB_WINPROBE),
> +	SNMP_MIB_ITEM("BacklogDrop", MPTCP_MIB_BACKLOGDROP),
> +	SNMP_MIB_ITEM("RcvPruned", MPTCP_MIB_RCVPRUNED),
>  };
>  
>  /* mptcp_mib_alloc - allocate percpu mib counters
> diff --git a/net/mptcp/mib.h b/net/mptcp/mib.h
> index 812218b5ed2b..c84eb853d499 100644
> --- a/net/mptcp/mib.h
> +++ b/net/mptcp/mib.h
> @@ -88,6 +88,8 @@ enum linux_mptcp_mib_field {
>  	MPTCP_MIB_SIMULTCONNFALLBACK,	/* Simultaneous connect */
>  	MPTCP_MIB_FALLBACKFAILED,	/* Can't fallback due to msk status */
>  	MPTCP_MIB_WINPROBE,		/* MPTCP-level zero window probe */
> +	MPTCP_MIB_BACKLOGDROP,		/* Backlog over memory limit */
> +	MPTCP_MIB_RCVPRUNED,		/* Dropped due to memory constrains */
>  	__MPTCP_MIB_MAX
>  };
>  
> diff --git a/net/mptcp/options.c b/net/mptcp/options.c
> index c664023d37ba..7b954ef78672 100644
> --- a/net/mptcp/options.c
> +++ b/net/mptcp/options.c
> @@ -1127,8 +1127,30 @@ static bool add_addr_hmac_valid(struct mptcp_sock *msk,
>  	return hmac == mp_opt->ahmac;
>  }
>  
> -/* Return false in case of error (or subflow has been reset),
> - * else return true.
> +static bool mptcp_over_limit(struct sock *sk, struct sock *ssk,
> +			     const struct sk_buff *skb)
> +{
> +	struct mptcp_sock *msk = mptcp_sk(sk);
> +	u64 mem = sk_rmem_alloc_get(sk);
> +
> +	mem += READ_ONCE(msk->backlog_len);
> +	if (likely(mem <= READ_ONCE(sk->sk_rcvbuf)))
> +		return false;
> +
> +	/* Avoid silently dropping pure acks, fin or zero win probes. */
> +	if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq ||
> +	    TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN ||
> +	    !after(TCP_SKB_CB(skb)->end_seq, tcp_sk(ssk)->rcv_nxt))
> +		return false;
> +
> +	/* Dropped due to memory constraints, schedule an ack. */
> +	inet_csk(ssk)->icsk_ack.pending |= ICSK_ACK_NOMEM | ICSK_ACK_NOW;
> +	inet_csk_schedule_ack(ssk);
> +	return true;
> +}
> +
> +/* Return false when the caller must drop the packet, i.e. in case of error,
> + * subflow has been reset, or over memory limits.
>   */
>  bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
>  {
> @@ -1154,7 +1176,7 @@ bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
>  
>  		__mptcp_data_acked(subflow->conn);
>  		mptcp_data_unlock(subflow->conn);
> -		return true;
> +		return !mptcp_over_limit(subflow->conn, sk, skb);
>  	}
>  
>  	mptcp_get_options(skb, &mp_opt);
> diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
> index 72b1fa3ca71c..5f7d8340a3d9 100644
> --- a/net/mptcp/protocol.c
> +++ b/net/mptcp/protocol.c
> @@ -381,6 +381,16 @@ static bool __mptcp_move_skb(struct sock *sk, struct sk_buff *skb)
>  
>  	mptcp_borrow_fwdmem(sk, skb);
>  
> +	/* Can't drop packets for fallback socket this late, or the stream
> +	 * will break.
> +	 */
> +	if (unlikely(sk_rmem_alloc_get(sk) > READ_ONCE(sk->sk_rcvbuf)) &&
> +	    !__mptcp_check_fallback(msk)) {
> +		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RCVPRUNED);
> +		mptcp_drop(sk, skb);

Here sashiko fears a possible forward-allocated memory leak. That is
sort of antinomy, as forward-allocated memory will be used for the next
skb(s) and excess fwd allocated memory will be still freed after the
next skb(s) processing or at sk close time. There is no real permanent leak.

We could release additionally allocated fwd memory in the error path as
a follow-up.

/P