[PATCH 7.2.y 0/4] mptcp: fix recent failed backports (20260919)

[PATCH 7.2.y 0/4] mptcp: fix recent failed backports (20260919)

[Matthieu Baerts (NGI0)]

The following patches could not be applied without conflicts in this
tree:

- 2b0f561f21b2 ("mptcp: avoid unneeded actions on subflow reset")
- 42064de57fb8 ("mptcp: close race between scheduler and state change")
- f3ef03357396 ("mptcp: fix bad accounting in __mptcp_subflow_push_pending()")

I backported the following commit to avoid conflicts:

- 6cafe51e0f98 ("mptcp: move the stale logic out of retrans scheduler")

Paolo Abeni (4):
  mptcp: move the stale logic out of retrans scheduler
  mptcp: avoid unneeded actions on subflow reset
  mptcp: close race between scheduler and state change
  mptcp: fix bad accounting in __mptcp_subflow_push_pending()

 net/mptcp/pm.c       | 41 +++++++++++++++++++++++++++--------------
 net/mptcp/protocol.c | 15 +++++++++------
 net/mptcp/protocol.h | 10 +++++++---
 net/mptcp/subflow.c  | 11 +++++++++++
 4 files changed, 54 insertions(+), 23 deletions(-)

-- 
2.55.0

[PATCH 7.2.y 1/4] mptcp: move the stale logic out of retrans scheduler

[Matthieu Baerts (NGI0)]

From: Paolo Abeni <pabeni@redhat.com>

commit 6cafe51e0f98fe60a106783d30b2f4c4b6039f4c upstream.

This allow separating the stale logic invocation and the retrans
scheduler, and will simplify the next patch.

It's also a cleaner design as the retrans scheduler has currently
too many side effects. As a possible downside, the retrans work will
now traverse the subflows list additional times; that does not matter
much, as this is slowpath.

While at it, pick more accurate names for the involved helpers and
explicitly note that the per subflow stale data is under msk socket
lock protection.

The scheduler and the stale logic may observe different subflow
statues, as no subflow lock is acquired. This is intentional and not
harmful, worst case leading to slower retransmissions.

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>
Link: https://patch.msgid.link/20260807-net-next-mptcp-oooq-pruning-v3-2-dbc1eb853cc3@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Stable-dep-of: 2b0f561f21b2 ("mptcp: avoid unneeded actions on subflow reset")
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
---
 net/mptcp/pm.c       | 41 +++++++++++++++++++++++++++--------------
 net/mptcp/protocol.c |  4 ++--
 net/mptcp/protocol.h | 11 +++++++----
 3 files changed, 36 insertions(+), 20 deletions(-)

diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index 4e1d65083b24..79bf88ca033b 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -1065,7 +1065,8 @@ bool mptcp_pm_is_backup(struct mptcp_sock *msk, struct sock_common *skc)
 	return mptcp_pm_nl_is_backup(msk, &skc_local);
 }
 
-static void mptcp_pm_subflows_chk_stale(const struct mptcp_sock *msk, struct sock *ssk)
+static void
+mptcp_pm_subflow_chk_stale(const struct mptcp_sock *msk, struct sock *ssk)
 {
 	struct mptcp_subflow_context *iter, *subflow = mptcp_subflow_ctx(ssk);
 	struct sock *sk = (struct sock *)msk;
@@ -1102,22 +1103,34 @@ static void mptcp_pm_subflows_chk_stale(const struct mptcp_sock *msk, struct soc
 	}
 }
 
-void mptcp_pm_subflow_chk_stale(const struct mptcp_sock *msk, struct sock *ssk)
+void mptcp_pm_chk_stale(const struct mptcp_sock *msk)
 {
-	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
-	u32 rcv_tstamp = READ_ONCE(tcp_sk(ssk)->rcv_tstamp);
+	struct mptcp_subflow_context *subflow;
 
-	/* keep track of rtx periods with no progress */
-	if (!subflow->stale_count) {
-		subflow->stale_rcv_tstamp = rcv_tstamp;
-		subflow->stale_count++;
-	} else if (subflow->stale_rcv_tstamp == rcv_tstamp) {
-		if (subflow->stale_count < U8_MAX)
+	mptcp_for_each_subflow(msk, subflow) {
+		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+		u32 rcv_tstamp;
+
+		if (!__mptcp_subflow_active(subflow))
+			continue;
+
+		/* No data outstanding at TCP level? not stale */
+		if (tcp_rtx_and_write_queues_empty(ssk))
+			continue;
+
+		/* keep track of rtx periods with no progress */
+		rcv_tstamp = READ_ONCE(tcp_sk(ssk)->rcv_tstamp);
+		if (!subflow->stale_count) {
+			subflow->stale_rcv_tstamp = rcv_tstamp;
 			subflow->stale_count++;
-		mptcp_pm_subflows_chk_stale(msk, ssk);
-	} else {
-		subflow->stale_count = 0;
-		mptcp_subflow_set_active(subflow);
+		} else if (subflow->stale_rcv_tstamp == rcv_tstamp) {
+			if (subflow->stale_count < U8_MAX)
+				subflow->stale_count++;
+			mptcp_pm_subflow_chk_stale(msk, ssk);
+		} else {
+			subflow->stale_count = 0;
+			mptcp_subflow_set_active(subflow);
+		}
 	}
 }
 
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 97523fa284d5..6db944b5c423 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -2471,7 +2471,6 @@ struct sock *mptcp_subflow_get_retrans(struct mptcp_sock *msk)
 
 		/* still data outstanding at TCP level? skip this */
 		if (!tcp_rtx_and_write_queues_empty(ssk)) {
-			mptcp_pm_subflow_chk_stale(msk, ssk);
 			min_stale_count = min_t(int, min_stale_count, subflow->stale_count);
 			continue;
 		}
@@ -2803,9 +2802,10 @@ static void __mptcp_retrans(struct sock *sk)
 	int ret, err;
 	u16 len = 0;
 
+	mptcp_pm_chk_stale(msk);
+
 	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) {
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index dbb40295165b..825533614468 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -581,12 +581,11 @@ struct mptcp_subflow_context {
 		remote_key_valid : 1,        /* received the peer key from */
 		disposable : 1,	    /* ctx can be free at ulp release time */
 		closing : 1,	    /* must not pass rx data to msk anymore */
-		stale : 1,	    /* unable to snd/rcv data, do not use for xmit */
 		valid_csum_seen : 1,        /* at least one csum validated */
 		is_mptfo : 1,	    /* subflow is doing TFO */
 		close_event_done : 1,       /* has done the post-closed part */
 		mpc_drop : 1,	    /* the MPC option has been dropped in a rtx */
-		__unused : 8;
+		__unused : 9;
 	bool	data_avail;
 	bool	scheduled;
 	bool	pm_listener;	    /* a listener managed by the kernel PM? */
@@ -605,7 +604,11 @@ struct mptcp_subflow_context {
 	u8	reset_seen:1;
 	u8	reset_transient:1;
 	u8	reset_reason:4;
-	u8	stale_count;
+	u8	stale_count;	    /* Protected by the msk socket lock */
+	u8	stale;		    /* Protected by the msk socket lock,
+				     * if set the subflow is unable to snd/rcv
+				     * data, the schedule should skip it
+				     */
 
 	u32	subflow_id;
 
@@ -1104,7 +1107,7 @@ int mptcp_pm_parse_entry(struct nlattr *attr, struct genl_info *info,
 bool mptcp_pm_addr_families_match(const struct sock *sk,
 				  const struct mptcp_addr_info *loc,
 				  const struct mptcp_addr_info *rem);
-void mptcp_pm_subflow_chk_stale(const struct mptcp_sock *msk, struct sock *ssk);
+void mptcp_pm_chk_stale(const struct mptcp_sock *msk);
 void mptcp_pm_new_connection(struct mptcp_sock *msk, const struct sock *ssk, int server_side);
 void mptcp_pm_fully_established(struct mptcp_sock *msk, const struct sock *ssk);
 bool mptcp_pm_allow_new_subflow(struct mptcp_sock *msk);
-- 
2.55.0

[PATCH 7.2.y 2/4] mptcp: avoid unneeded actions on subflow reset

[Matthieu Baerts (NGI0)]

From: Paolo Abeni <pabeni@redhat.com>

commit 2b0f561f21b27c40c91ea4975268a06092bd7e9c upstream.

Once in a blue moon, the mptcp receive path can recursively call
mptcp_data_ready() via state change under unlucky error conditions, and
then try to hold the data lock again.

Break the recursion loop explicitly checking for the exceptional
condition.

Add a new flag instead of using an existing one like 'closing', to exit
early in subflow_state_change(), and explicitly flush the RX queue at
reset time.

This avoids unneeded processing to check for available data -- calling
get_mapping_status() and more on a dying subflow -- but also in error
reporting and worker scheduling.

Note that we must consume the currently peeked skb before invoking
mptcp_dss_corruption to avoid consuming it again after the eventual
reset has freed it.

Fixes: e32d262c89e2 ("mptcp: handle consistently DSS corruption")
Cc: stable@vger.kernel.org
Reported-by: Xinyang Ge <xinyang@anthropic.com>
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>
Link: https://patch.msgid.link/20260917-net-mptcp-misc-fixes-7-3-rc4-v2-1-0cf5c72667c8@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
---
 net/mptcp/protocol.c |  4 ++--
 net/mptcp/protocol.h |  3 ++-
 net/mptcp/subflow.c  | 11 +++++++++++
 3 files changed, 15 insertions(+), 3 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 6db944b5c423..b6581858979d 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -773,12 +773,12 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk,
 				mptcp_dss_corruption(msk, ssk);
 			}
 		} else {
+			sk_eat_skb(ssk, skb);
+
 			if (unlikely(!fin)) {
 				DEBUG_NET_WARN_ON_ONCE(1);
 				mptcp_dss_corruption(msk, ssk);
 			}
-
-			sk_eat_skb(ssk, skb);
 		}
 
 		WRITE_ONCE(tp->copied_seq, seq);
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 825533614468..d44aaa783c22 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -585,7 +585,8 @@ struct mptcp_subflow_context {
 		is_mptfo : 1,	    /* subflow is doing TFO */
 		close_event_done : 1,       /* has done the post-closed part */
 		mpc_drop : 1,	    /* the MPC option has been dropped in a rtx */
-		__unused : 9;
+		resetting : 1,	    /* subflow is resetting */
+		__unused : 8;
 	bool	data_avail;
 	bool	scheduled;
 	bool	pm_listener;	    /* a listener managed by the kernel PM? */
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index bde79720098a..edd33dc9367f 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -436,6 +436,10 @@ void mptcp_subflow_reset(struct sock *ssk)
 	/* must hold: tcp_done() could drop last reference on parent */
 	sock_hold(sk);
 
+	subflow->resetting = 1;
+
+	/* No need to delay the actual close for to-be discarded data. */
+	__skb_queue_purge(&ssk->sk_receive_queue);
 	mptcp_send_active_reset_reason(ssk);
 	tcp_done(ssk);
 	if (!test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &mptcp_sk(sk)->flags))
@@ -1873,6 +1877,13 @@ static void subflow_state_change(struct sock *sk)
 
 	__subflow_state_change(sk);
 
+	/* Rx queue processing is unneeded, error reporting will take place at
+	 * __mptcp_close_ssk() time and subflow reset can't happen in case of
+	 * fallback: subflow_sched_work_if_closed() would be a no-op.
+	 */
+	if (subflow->resetting)
+		return;
+
 	/* as recvmsg() does not acquire the subflow socket for ssk selection
 	 * a fin packet carrying a DSS can be unnoticed if we don't trigger
 	 * the data available machinery here.
-- 
2.55.0

[PATCH 7.2.y 3/4] mptcp: close race between scheduler and state change

[Matthieu Baerts (NGI0)]

From: Paolo Abeni <pabeni@redhat.com>

commit 42064de57fb83231fcc89663a94885f228a1ee53 upstream.

The mptcp scheduler may race with subflow sockets state change: data
transmission on the selected socket may fail and a later release could
try to use mss_now reset to 0 for a divide operation.

Address the issue by explicitly checking for the critical scenario.

Fixes: c886d70286bf ("mptcp: do not queue data on closed subflows")
Cc: stable@vger.kernel.org
Reported-by: Shardul Bankar <shardul.b@mpiricsoftware.com>
Reported-by: Xinyang Ge <xinyang@anthropic.com>
Closes: https://lore.kernel.org/20260525194828.1137119-1-shardul.b@mpiricsoftware.com
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>
Link: https://patch.msgid.link/20260917-net-mptcp-misc-fixes-7-3-rc4-v2-2-0cf5c72667c8@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
---
 net/mptcp/protocol.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index b6581858979d..99fd31036222 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1588,7 +1588,9 @@ struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)
 
 static void mptcp_push_release(struct sock *ssk, struct mptcp_sendmsg_info *info)
 {
-	tcp_push(ssk, 0, info->mss_now, tcp_sk(ssk)->nonagle, info->size_goal);
+	if (info->mss_now)
+		tcp_push(ssk, 0, info->mss_now, tcp_sk(ssk)->nonagle,
+			 info->size_goal);
 	release_sock(ssk);
 }
 
-- 
2.55.0

[PATCH 7.2.y 4/4] mptcp: fix bad accounting in __mptcp_subflow_push_pending()

[Matthieu Baerts (NGI0)]

From: Paolo Abeni <pabeni@redhat.com>

commit f3ef03357396d4b147d8e76c75fb612c2f264ffc upstream.

If __subflow_push_pending() errors out we should avoid updating the
copied byte counters, to avoid mismatch push call later on.

Fixes: 0fa1b3783a17 ("mptcp: use get_send wrapper")
Cc: stable@vger.kernel.org
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>
Link: https://patch.msgid.link/20260917-net-mptcp-misc-fixes-7-3-rc4-v2-3-0cf5c72667c8@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
---
 net/mptcp/protocol.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 99fd31036222..49c46498af96 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1778,7 +1778,8 @@ static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk, bool
 			ret = __subflow_push_pending(sk, ssk, &info);
 			if (ret <= 0)
 				keep_pushing = false;
-			copied += ret;
+			else
+				copied += ret;
 		}
 
 		mptcp_for_each_subflow(msk, subflow) {
-- 
2.55.0

Patch "mptcp: close race between scheduler and state change" has been added to the 7.2-stable tree

[gregkh]

This is a note to let you know that I've just added the patch titled

    mptcp: close race between scheduler and state change

to the 7.2-stable tree which can be found at:
    http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary

The filename of the patch is:
     mptcp-close-race-between-scheduler-and-state-change.patch
and it can be found in the queue-7.2 subdirectory.

If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@vger.kernel.org> know about it.


From stable+bounces-338590-greg=kroah.com@vger.kernel.org Sat Sep 19 21:36:25 2026
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Sat, 19 Sep 2026 21:35:45 +0200
Subject: mptcp: close race between scheduler and state change
To: mptcp@lists.linux.dev, stable@vger.kernel.org, gregkh@linuxfoundation.org
Cc: Paolo Abeni <pabeni@redhat.com>, sashal@kernel.org, Shardul Bankar <shardul.b@mpiricsoftware.com>, Xinyang Ge <xinyang@anthropic.com>, "Matthieu Baerts (NGI0)" <matttbe@kernel.org>, Jakub Kicinski <kuba@kernel.org>
Message-ID: <20260919193541.1915297-9-matttbe@kernel.org>

From: Paolo Abeni <pabeni@redhat.com>

commit 42064de57fb83231fcc89663a94885f228a1ee53 upstream.

The mptcp scheduler may race with subflow sockets state change: data
transmission on the selected socket may fail and a later release could
try to use mss_now reset to 0 for a divide operation.

Address the issue by explicitly checking for the critical scenario.

Fixes: c886d70286bf ("mptcp: do not queue data on closed subflows")
Cc: stable@vger.kernel.org
Reported-by: Shardul Bankar <shardul.b@mpiricsoftware.com>
Reported-by: Xinyang Ge <xinyang@anthropic.com>
Closes: https://lore.kernel.org/20260525194828.1137119-1-shardul.b@mpiricsoftware.com
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>
Link: https://patch.msgid.link/20260917-net-mptcp-misc-fixes-7-3-rc4-v2-2-0cf5c72667c8@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 net/mptcp/protocol.c |    4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1588,7 +1588,9 @@ struct sock *mptcp_subflow_get_send(stru
 
 static void mptcp_push_release(struct sock *ssk, struct mptcp_sendmsg_info *info)
 {
-	tcp_push(ssk, 0, info->mss_now, tcp_sk(ssk)->nonagle, info->size_goal);
+	if (info->mss_now)
+		tcp_push(ssk, 0, info->mss_now, tcp_sk(ssk)->nonagle,
+			 info->size_goal);
 	release_sock(ssk);
 }
 


Patches currently in stable-queue which might be from matttbe@kernel.org are

queue-7.2/selftests-mptcp-fix-an-uaf-in-mptcp_connect.c.patch
queue-7.2/mptcp-fix-bad-accounting-in-__mptcp_subflow_push_pending.patch
queue-7.2/mptcp-pm-reset-retrans_time-when-add_addr-entry-is-reused.patch
queue-7.2/mptcp-syncookies-remember-the-request-backup-flag.patch
queue-7.2/mptcp-remove-unneeded-read_once-annotation.patch
queue-7.2/mptcp-options-fix-uninit-value-in-mptcp_write_data_fin.patch
queue-7.2/mptcp-pm-kernel-drop-pending-add_addr-when-removing-id0.patch
queue-7.2/mptcp-close-race-between-scheduler-and-state-change.patch
queue-7.2/selftests-mptcp-lib-get-counters-for-the-right-test.patch
queue-7.2/tcp-use-gfp_atomic-in-tcp_send_active_reset.patch
queue-7.2/mptcp-do-not-reschedule-the-rtx-timer-for-fallback-sockets.patch
queue-7.2/mptcp-pm-userspace-fix-address-id-overflow.patch
queue-7.2/mptcp-move-the-stale-logic-out-of-retrans-scheduler.patch
queue-7.2/mptcp-avoid-unneeded-actions-on-subflow-reset.patch
queue-7.2/selftests-mptcp-lib-dump-nstat-for-the-right-test.patch
queue-7.2/mptcp-options-handle-mpc-data-csum-reqd-no-csum.patch
queue-7.2/mptcp-prevent-race-between-disconnect-and-rtx.patch
queue-7.2/mptcp-subflow-no-need-to-copy-thmac-during-ulp_clone.patch

Patch "mptcp: fix bad accounting in __mptcp_subflow_push_pending()" has been added to the 7.2-stable tree

[gregkh]

This is a note to let you know that I've just added the patch titled

    mptcp: fix bad accounting in __mptcp_subflow_push_pending()

to the 7.2-stable tree which can be found at:
    http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary

The filename of the patch is:
     mptcp-fix-bad-accounting-in-__mptcp_subflow_push_pending.patch
and it can be found in the queue-7.2 subdirectory.

If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@vger.kernel.org> know about it.


From matttbe@kernel.org Sat Sep 19 21:36:13 2026
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Sat, 19 Sep 2026 21:35:46 +0200
Subject: mptcp: fix bad accounting in __mptcp_subflow_push_pending()
To: mptcp@lists.linux.dev, stable@vger.kernel.org, gregkh@linuxfoundation.org
Cc: Paolo Abeni <pabeni@redhat.com>, sashal@kernel.org, "Matthieu Baerts (NGI0)" <matttbe@kernel.org>, Jakub Kicinski <kuba@kernel.org>
Message-ID: <20260919193541.1915297-10-matttbe@kernel.org>

From: Paolo Abeni <pabeni@redhat.com>

commit f3ef03357396d4b147d8e76c75fb612c2f264ffc upstream.

If __subflow_push_pending() errors out we should avoid updating the
copied byte counters, to avoid mismatch push call later on.

Fixes: 0fa1b3783a17 ("mptcp: use get_send wrapper")
Cc: stable@vger.kernel.org
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>
Link: https://patch.msgid.link/20260917-net-mptcp-misc-fixes-7-3-rc4-v2-3-0cf5c72667c8@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 net/mptcp/protocol.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1778,7 +1778,8 @@ static void __mptcp_subflow_push_pending
 			ret = __subflow_push_pending(sk, ssk, &info);
 			if (ret <= 0)
 				keep_pushing = false;
-			copied += ret;
+			else
+				copied += ret;
 		}
 
 		mptcp_for_each_subflow(msk, subflow) {


Patches currently in stable-queue which might be from matttbe@kernel.org are

queue-7.2/selftests-mptcp-fix-an-uaf-in-mptcp_connect.c.patch
queue-7.2/mptcp-fix-bad-accounting-in-__mptcp_subflow_push_pending.patch
queue-7.2/mptcp-pm-reset-retrans_time-when-add_addr-entry-is-reused.patch
queue-7.2/mptcp-syncookies-remember-the-request-backup-flag.patch
queue-7.2/mptcp-remove-unneeded-read_once-annotation.patch
queue-7.2/mptcp-options-fix-uninit-value-in-mptcp_write_data_fin.patch
queue-7.2/mptcp-pm-kernel-drop-pending-add_addr-when-removing-id0.patch
queue-7.2/mptcp-close-race-between-scheduler-and-state-change.patch
queue-7.2/selftests-mptcp-lib-get-counters-for-the-right-test.patch
queue-7.2/tcp-use-gfp_atomic-in-tcp_send_active_reset.patch
queue-7.2/mptcp-do-not-reschedule-the-rtx-timer-for-fallback-sockets.patch
queue-7.2/mptcp-pm-userspace-fix-address-id-overflow.patch
queue-7.2/mptcp-move-the-stale-logic-out-of-retrans-scheduler.patch
queue-7.2/mptcp-avoid-unneeded-actions-on-subflow-reset.patch
queue-7.2/selftests-mptcp-lib-dump-nstat-for-the-right-test.patch
queue-7.2/mptcp-options-handle-mpc-data-csum-reqd-no-csum.patch
queue-7.2/mptcp-prevent-race-between-disconnect-and-rtx.patch
queue-7.2/mptcp-subflow-no-need-to-copy-thmac-during-ulp_clone.patch

Patch "mptcp: avoid unneeded actions on subflow reset" has been added to the 7.2-stable tree

[gregkh]

This is a note to let you know that I've just added the patch titled

    mptcp: avoid unneeded actions on subflow reset

to the 7.2-stable tree which can be found at:
    http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary

The filename of the patch is:
     mptcp-avoid-unneeded-actions-on-subflow-reset.patch
and it can be found in the queue-7.2 subdirectory.

If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@vger.kernel.org> know about it.


From stable+bounces-338589-greg=kroah.com@vger.kernel.org Sat Sep 19 21:36:20 2026
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Sat, 19 Sep 2026 21:35:44 +0200
Subject: mptcp: avoid unneeded actions on subflow reset
To: mptcp@lists.linux.dev, stable@vger.kernel.org, gregkh@linuxfoundation.org
Cc: Paolo Abeni <pabeni@redhat.com>, sashal@kernel.org, Xinyang Ge <xinyang@anthropic.com>, "Matthieu Baerts (NGI0)" <matttbe@kernel.org>, Jakub Kicinski <kuba@kernel.org>
Message-ID: <20260919193541.1915297-8-matttbe@kernel.org>

From: Paolo Abeni <pabeni@redhat.com>

commit 2b0f561f21b27c40c91ea4975268a06092bd7e9c upstream.

Once in a blue moon, the mptcp receive path can recursively call
mptcp_data_ready() via state change under unlucky error conditions, and
then try to hold the data lock again.

Break the recursion loop explicitly checking for the exceptional
condition.

Add a new flag instead of using an existing one like 'closing', to exit
early in subflow_state_change(), and explicitly flush the RX queue at
reset time.

This avoids unneeded processing to check for available data -- calling
get_mapping_status() and more on a dying subflow -- but also in error
reporting and worker scheduling.

Note that we must consume the currently peeked skb before invoking
mptcp_dss_corruption to avoid consuming it again after the eventual
reset has freed it.

Fixes: e32d262c89e2 ("mptcp: handle consistently DSS corruption")
Cc: stable@vger.kernel.org
Reported-by: Xinyang Ge <xinyang@anthropic.com>
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>
Link: https://patch.msgid.link/20260917-net-mptcp-misc-fixes-7-3-rc4-v2-1-0cf5c72667c8@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 net/mptcp/protocol.c |    4 ++--
 net/mptcp/protocol.h |    3 ++-
 net/mptcp/subflow.c  |   11 +++++++++++
 3 files changed, 15 insertions(+), 3 deletions(-)

--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -773,12 +773,12 @@ static bool __mptcp_move_skbs_from_subfl
 				mptcp_dss_corruption(msk, ssk);
 			}
 		} else {
+			sk_eat_skb(ssk, skb);
+
 			if (unlikely(!fin)) {
 				DEBUG_NET_WARN_ON_ONCE(1);
 				mptcp_dss_corruption(msk, ssk);
 			}
-
-			sk_eat_skb(ssk, skb);
 		}
 
 		WRITE_ONCE(tp->copied_seq, seq);
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -585,7 +585,8 @@ struct mptcp_subflow_context {
 		is_mptfo : 1,	    /* subflow is doing TFO */
 		close_event_done : 1,       /* has done the post-closed part */
 		mpc_drop : 1,	    /* the MPC option has been dropped in a rtx */
-		__unused : 9;
+		resetting : 1,	    /* subflow is resetting */
+		__unused : 8;
 	bool	data_avail;
 	bool	scheduled;
 	bool	pm_listener;	    /* a listener managed by the kernel PM? */
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -436,6 +436,10 @@ void mptcp_subflow_reset(struct sock *ss
 	/* must hold: tcp_done() could drop last reference on parent */
 	sock_hold(sk);
 
+	subflow->resetting = 1;
+
+	/* No need to delay the actual close for to-be discarded data. */
+	__skb_queue_purge(&ssk->sk_receive_queue);
 	mptcp_send_active_reset_reason(ssk);
 	tcp_done(ssk);
 	if (!test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &mptcp_sk(sk)->flags))
@@ -1873,6 +1877,13 @@ static void subflow_state_change(struct
 
 	__subflow_state_change(sk);
 
+	/* Rx queue processing is unneeded, error reporting will take place at
+	 * __mptcp_close_ssk() time and subflow reset can't happen in case of
+	 * fallback: subflow_sched_work_if_closed() would be a no-op.
+	 */
+	if (subflow->resetting)
+		return;
+
 	/* as recvmsg() does not acquire the subflow socket for ssk selection
 	 * a fin packet carrying a DSS can be unnoticed if we don't trigger
 	 * the data available machinery here.


Patches currently in stable-queue which might be from matttbe@kernel.org are

queue-7.2/selftests-mptcp-fix-an-uaf-in-mptcp_connect.c.patch
queue-7.2/mptcp-fix-bad-accounting-in-__mptcp_subflow_push_pending.patch
queue-7.2/mptcp-pm-reset-retrans_time-when-add_addr-entry-is-reused.patch
queue-7.2/mptcp-syncookies-remember-the-request-backup-flag.patch
queue-7.2/mptcp-remove-unneeded-read_once-annotation.patch
queue-7.2/mptcp-options-fix-uninit-value-in-mptcp_write_data_fin.patch
queue-7.2/mptcp-pm-kernel-drop-pending-add_addr-when-removing-id0.patch
queue-7.2/mptcp-close-race-between-scheduler-and-state-change.patch
queue-7.2/selftests-mptcp-lib-get-counters-for-the-right-test.patch
queue-7.2/tcp-use-gfp_atomic-in-tcp_send_active_reset.patch
queue-7.2/mptcp-do-not-reschedule-the-rtx-timer-for-fallback-sockets.patch
queue-7.2/mptcp-pm-userspace-fix-address-id-overflow.patch
queue-7.2/mptcp-move-the-stale-logic-out-of-retrans-scheduler.patch
queue-7.2/mptcp-avoid-unneeded-actions-on-subflow-reset.patch
queue-7.2/selftests-mptcp-lib-dump-nstat-for-the-right-test.patch
queue-7.2/mptcp-options-handle-mpc-data-csum-reqd-no-csum.patch
queue-7.2/mptcp-prevent-race-between-disconnect-and-rtx.patch
queue-7.2/mptcp-subflow-no-need-to-copy-thmac-during-ulp_clone.patch

Patch "mptcp: move the stale logic out of retrans scheduler" has been added to the 7.2-stable tree

[gregkh]

This is a note to let you know that I've just added the patch titled

    mptcp: move the stale logic out of retrans scheduler

to the 7.2-stable tree which can be found at:
    http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary

The filename of the patch is:
     mptcp-move-the-stale-logic-out-of-retrans-scheduler.patch
and it can be found in the queue-7.2 subdirectory.

If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@vger.kernel.org> know about it.


From stable+bounces-338588-greg=kroah.com@vger.kernel.org Sat Sep 19 21:36:15 2026
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Sat, 19 Sep 2026 21:35:43 +0200
Subject: mptcp: move the stale logic out of retrans scheduler
To: mptcp@lists.linux.dev, stable@vger.kernel.org, gregkh@linuxfoundation.org
Cc: Paolo Abeni <pabeni@redhat.com>, sashal@kernel.org, "Matthieu Baerts (NGI0)" <matttbe@kernel.org>, Jakub Kicinski <kuba@kernel.org>
Message-ID: <20260919193541.1915297-7-matttbe@kernel.org>

From: Paolo Abeni <pabeni@redhat.com>

commit 6cafe51e0f98fe60a106783d30b2f4c4b6039f4c upstream.

This allow separating the stale logic invocation and the retrans
scheduler, and will simplify the next patch.

It's also a cleaner design as the retrans scheduler has currently
too many side effects. As a possible downside, the retrans work will
now traverse the subflows list additional times; that does not matter
much, as this is slowpath.

While at it, pick more accurate names for the involved helpers and
explicitly note that the per subflow stale data is under msk socket
lock protection.

The scheduler and the stale logic may observe different subflow
statues, as no subflow lock is acquired. This is intentional and not
harmful, worst case leading to slower retransmissions.

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>
Link: https://patch.msgid.link/20260807-net-next-mptcp-oooq-pruning-v3-2-dbc1eb853cc3@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Stable-dep-of: 2b0f561f21b2 ("mptcp: avoid unneeded actions on subflow reset")
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 net/mptcp/pm.c       |   41 +++++++++++++++++++++++++++--------------
 net/mptcp/protocol.c |    4 ++--
 net/mptcp/protocol.h |   11 +++++++----
 3 files changed, 36 insertions(+), 20 deletions(-)

--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -1065,7 +1065,8 @@ bool mptcp_pm_is_backup(struct mptcp_soc
 	return mptcp_pm_nl_is_backup(msk, &skc_local);
 }
 
-static void mptcp_pm_subflows_chk_stale(const struct mptcp_sock *msk, struct sock *ssk)
+static void
+mptcp_pm_subflow_chk_stale(const struct mptcp_sock *msk, struct sock *ssk)
 {
 	struct mptcp_subflow_context *iter, *subflow = mptcp_subflow_ctx(ssk);
 	struct sock *sk = (struct sock *)msk;
@@ -1102,22 +1103,34 @@ static void mptcp_pm_subflows_chk_stale(
 	}
 }
 
-void mptcp_pm_subflow_chk_stale(const struct mptcp_sock *msk, struct sock *ssk)
+void mptcp_pm_chk_stale(const struct mptcp_sock *msk)
 {
-	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
-	u32 rcv_tstamp = READ_ONCE(tcp_sk(ssk)->rcv_tstamp);
+	struct mptcp_subflow_context *subflow;
 
-	/* keep track of rtx periods with no progress */
-	if (!subflow->stale_count) {
-		subflow->stale_rcv_tstamp = rcv_tstamp;
-		subflow->stale_count++;
-	} else if (subflow->stale_rcv_tstamp == rcv_tstamp) {
-		if (subflow->stale_count < U8_MAX)
+	mptcp_for_each_subflow(msk, subflow) {
+		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+		u32 rcv_tstamp;
+
+		if (!__mptcp_subflow_active(subflow))
+			continue;
+
+		/* No data outstanding at TCP level? not stale */
+		if (tcp_rtx_and_write_queues_empty(ssk))
+			continue;
+
+		/* keep track of rtx periods with no progress */
+		rcv_tstamp = READ_ONCE(tcp_sk(ssk)->rcv_tstamp);
+		if (!subflow->stale_count) {
+			subflow->stale_rcv_tstamp = rcv_tstamp;
 			subflow->stale_count++;
-		mptcp_pm_subflows_chk_stale(msk, ssk);
-	} else {
-		subflow->stale_count = 0;
-		mptcp_subflow_set_active(subflow);
+		} else if (subflow->stale_rcv_tstamp == rcv_tstamp) {
+			if (subflow->stale_count < U8_MAX)
+				subflow->stale_count++;
+			mptcp_pm_subflow_chk_stale(msk, ssk);
+		} else {
+			subflow->stale_count = 0;
+			mptcp_subflow_set_active(subflow);
+		}
 	}
 }
 
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -2471,7 +2471,6 @@ struct sock *mptcp_subflow_get_retrans(s
 
 		/* still data outstanding at TCP level? skip this */
 		if (!tcp_rtx_and_write_queues_empty(ssk)) {
-			mptcp_pm_subflow_chk_stale(msk, ssk);
 			min_stale_count = min_t(int, min_stale_count, subflow->stale_count);
 			continue;
 		}
@@ -2803,9 +2802,10 @@ static void __mptcp_retrans(struct sock
 	int ret, err;
 	u16 len = 0;
 
+	mptcp_pm_chk_stale(msk);
+
 	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) {
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -581,12 +581,11 @@ struct mptcp_subflow_context {
 		remote_key_valid : 1,        /* received the peer key from */
 		disposable : 1,	    /* ctx can be free at ulp release time */
 		closing : 1,	    /* must not pass rx data to msk anymore */
-		stale : 1,	    /* unable to snd/rcv data, do not use for xmit */
 		valid_csum_seen : 1,        /* at least one csum validated */
 		is_mptfo : 1,	    /* subflow is doing TFO */
 		close_event_done : 1,       /* has done the post-closed part */
 		mpc_drop : 1,	    /* the MPC option has been dropped in a rtx */
-		__unused : 8;
+		__unused : 9;
 	bool	data_avail;
 	bool	scheduled;
 	bool	pm_listener;	    /* a listener managed by the kernel PM? */
@@ -605,7 +604,11 @@ struct mptcp_subflow_context {
 	u8	reset_seen:1;
 	u8	reset_transient:1;
 	u8	reset_reason:4;
-	u8	stale_count;
+	u8	stale_count;	    /* Protected by the msk socket lock */
+	u8	stale;		    /* Protected by the msk socket lock,
+				     * if set the subflow is unable to snd/rcv
+				     * data, the schedule should skip it
+				     */
 
 	u32	subflow_id;
 
@@ -1104,7 +1107,7 @@ int mptcp_pm_parse_entry(struct nlattr *
 bool mptcp_pm_addr_families_match(const struct sock *sk,
 				  const struct mptcp_addr_info *loc,
 				  const struct mptcp_addr_info *rem);
-void mptcp_pm_subflow_chk_stale(const struct mptcp_sock *msk, struct sock *ssk);
+void mptcp_pm_chk_stale(const struct mptcp_sock *msk);
 void mptcp_pm_new_connection(struct mptcp_sock *msk, const struct sock *ssk, int server_side);
 void mptcp_pm_fully_established(struct mptcp_sock *msk, const struct sock *ssk);
 bool mptcp_pm_allow_new_subflow(struct mptcp_sock *msk);


Patches currently in stable-queue which might be from matttbe@kernel.org are

queue-7.2/selftests-mptcp-fix-an-uaf-in-mptcp_connect.c.patch
queue-7.2/mptcp-fix-bad-accounting-in-__mptcp_subflow_push_pending.patch
queue-7.2/mptcp-pm-reset-retrans_time-when-add_addr-entry-is-reused.patch
queue-7.2/mptcp-syncookies-remember-the-request-backup-flag.patch
queue-7.2/mptcp-remove-unneeded-read_once-annotation.patch
queue-7.2/mptcp-options-fix-uninit-value-in-mptcp_write_data_fin.patch
queue-7.2/mptcp-pm-kernel-drop-pending-add_addr-when-removing-id0.patch
queue-7.2/mptcp-close-race-between-scheduler-and-state-change.patch
queue-7.2/selftests-mptcp-lib-get-counters-for-the-right-test.patch
queue-7.2/tcp-use-gfp_atomic-in-tcp_send_active_reset.patch
queue-7.2/mptcp-do-not-reschedule-the-rtx-timer-for-fallback-sockets.patch
queue-7.2/mptcp-pm-userspace-fix-address-id-overflow.patch
queue-7.2/mptcp-move-the-stale-logic-out-of-retrans-scheduler.patch
queue-7.2/mptcp-avoid-unneeded-actions-on-subflow-reset.patch
queue-7.2/selftests-mptcp-lib-dump-nstat-for-the-right-test.patch
queue-7.2/mptcp-options-handle-mpc-data-csum-reqd-no-csum.patch
queue-7.2/mptcp-prevent-race-between-disconnect-and-rtx.patch
queue-7.2/mptcp-subflow-no-need-to-copy-thmac-during-ulp_clone.patch