Skip to contentSkip to conversation

FAILED: patch "[PATCH] mptcp: add-addr: always drop other suboptions" failed to apply to 6.1-stable tree

PATCH New [email protected] 2 participants 3 messages Jun 15 – Jun 16

Subsystems (3)
lore
Share & tools
lore

[email protected]

author maintainer
#0 lore raw

The patch below does not apply to the 6.1-stable tree.
If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <[email protected]>.

To reproduce the conflict and resubmit, you may use the following commands:

git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y
git checkout FETCH_HEAD
git cherry-pick -x bd34fa0257261b76964df1c98f44b3cb4ee14620
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<[email protected]>' --in-reply-to '2026061515-snowsuit-tackling-58ce@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^..

Possible dependencies:

thanks,

greg k-h

------------------ original commit in Linus's tree ------------------

From bd34fa0257261b76964df1c98f44b3cb4ee14620 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <[email protected]>
Date: Tue, 2 Jun 2026 22:14:18 +1000
Subject: [PATCH] mptcp: add-addr: always drop other suboptions

When an ADD_ADDR needs to be sent, it could be prepared if there is enough remaining space and even if the packet is not a pure ACK. But it would be dropped soon after.

Indeed, in mptcp_pm_add_addr_signal(), there is enough space to fit a DSS of 20 octets and an ADD_ADDR echo containing an IPv4 address on 8 octets for example. In this case, the packet would be prepared, the MPTCP_ADD_ADDR_ECHO bit would be removed from pm->addr_signal, but the option would be silently dropped in mptcp_established_options_add_addr() not to override DSS info in the union from 'struct mptcp_out_options', and also because mptcp_write_options() will enforce mutually exclusion with DSS.

Instead, don't even try to send an ADD_ADDR if it is not a pure ACK. Retry for each new packet until a pure-ACK is emitted. That's fine to do that, because each time an ADD_ADDR (echo) is scheduled, a pure ACK is queued.

This also simplifies the code, and the skb checks can be done earlier, before the lock.

Note: also, since commit 6d0060f600ad ("mptcp: Write MPTCP DSS headers to outgoing data packets"), opts->ahmac would not have been set to 0 when other suboptions were not dropped, and when sending an ADD_ADDR echo. That would have resulted in sending an ADD_ADDR using garbage info, where there was not enough space, instead of an echo one without the ADD_ADDR HMAC.

net/mptcp/options.c +7 -23
index f9f587203c35..b3ea7854818f 100644
@@ -665,7 +665,6 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff *
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
 	struct mptcp_sock *msk = mptcp_sk(subflow->conn);
-	bool drop_other_suboptions = false;
 	unsigned int opt_size = *size;
 	struct mptcp_addr_info addr;
 	bool echo;
@@ -676,36 +675,20 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff *
 	 */
 	if (!mptcp_pm_should_add_signal(msk) ||
 	    (opts->suboptions & (OPTION_MPTCP_MPJ_ACK | OPTION_MPTCP_MPC_ACK)) ||
-	    !mptcp_pm_add_addr_signal(msk, skb, opt_size, remaining, &addr,
-		    &echo, &drop_other_suboptions))
+	    !skb || !skb_is_tcp_pure_ack(skb) ||
+	    !mptcp_pm_add_addr_signal(msk, opt_size, remaining, &addr, &echo))
 		return false;
 
-	/*
-	 * Later on, mptcp_write_options() will enforce mutually exclusion with
-	 * DSS, bail out if such option is set and we can't drop it.
-	 */
-	if (drop_other_suboptions)
-		remaining += opt_size;
-	else if (opts->suboptions & OPTION_MPTCP_DSS)
-		return false;
+	remaining += opt_size;
 
 	len = mptcp_add_addr_len(addr.family, echo, !!addr.port);
 	if (remaining < len)
 		return false;
 
 	*size = len;
-	if (drop_other_suboptions) {
-		pr_debug("drop other suboptions\n");
-		opts->suboptions = 0;
-
-		/* note that e.g. DSS could have written into the memory
-		 * aliased by ahmac, we must reset the field here
-		 * to avoid appending the hmac even for ADD_ADDR echo
-		 * options
-		 */
-		opts->ahmac = 0;
-		*size -= opt_size;
-	}
+	pr_debug("drop other suboptions\n");
+	opts->suboptions = 0;
+	*size -= opt_size;
 	opts->addr = addr;
 	opts->suboptions |= OPTION_MPTCP_ADD_ADDR;
 	if (!echo) {
@@ -715,6 +698,7 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff *
 						     &opts->addr);
 	} else {
 		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ECHOADDTX);
+		opts->ahmac = 0;
 	}
 	pr_debug("addr_id=%d, ahmac=%llu, echo=%d, port=%d\n",
 		 opts->addr.id, opts->ahmac, echo, ntohs(opts->addr.port));
net/mptcp/pm.c +4 -11
index 3e770c7407e1..470501470fe5 100644
@@ -887,10 +887,9 @@ void mptcp_pm_mp_fail_received(struct sock *sk, u64 fail_seq)
 	}
 }
 
-bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, const struct sk_buff *skb,
-			      unsigned int opt_size, unsigned int remaining,
-			      struct mptcp_addr_info *addr, bool *echo,
-			      bool *drop_other_suboptions)
+bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, unsigned int opt_size,
+			      unsigned int remaining,
+			      struct mptcp_addr_info *addr, bool *echo)
 {
 	bool skip_add_addr = false;
 	int ret = false;
@@ -908,10 +907,7 @@ bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, const struct sk_buff *skb,
 	 * plain dup-ack from TCP perspective. The other MPTCP-relevant info,
 	 * if any, will be carried by the 'original' TCP ack
 	 */
-	if (skb && skb_is_tcp_pure_ack(skb)) {
-		remaining += opt_size;
-		*drop_other_suboptions = true;
-	}
+	remaining += opt_size;
 
 	*echo = mptcp_pm_should_add_signal_echo(msk);
 	if (*echo) {
@@ -929,9 +925,6 @@ bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, const struct sk_buff *skb,
 	if (remaining < mptcp_add_addr_len(family, *echo, port)) {
 		struct net *net = sock_net((struct sock *)msk);
 
-		if (!*drop_other_suboptions)
-			goto out_unlock;
-
 		if (*echo) {
 			MPTCP_INC_STATS(net, MPTCP_MIB_ECHOADDTXDROP);
 		} else {
net/mptcp/protocol.h +3 -4
index e4f5aba24da7..b93b878478d2 100644
@@ -1229,10 +1229,9 @@ static inline int mptcp_rm_addr_len(const struct mptcp_rm_list *rm_list)
 	return TCPOLEN_MPTCP_RM_ADDR_BASE + roundup(rm_list->nr - 1, 4) + 1;
 }
 
-bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, const struct sk_buff *skb,
-			      unsigned int opt_size, unsigned int remaining,
-			      struct mptcp_addr_info *addr, bool *echo,
-			      bool *drop_other_suboptions);
+bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, unsigned int opt_size,
+			      unsigned int remaining,
+			      struct mptcp_addr_info *addr, bool *echo);
 bool mptcp_pm_rm_addr_signal(struct mptcp_sock *msk, unsigned int remaining,
 			     struct mptcp_rm_list *rm_list);
 int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc);
maintainer
#1 lore raw

PATCH 1/2 mptcp: pm: fix ADD_ADDR timer infinite retry on option space insufficient

From: Li Xiasong <[email protected]>

[ Upstream commit 51e398a3b8961b26a8c0a4ba9a777c5339791707 ]

When TCP option space is insufficient (e.g., when sending ADD_ADDR with an IPv6 address and port while tcp_timestamps is enabled), the original code jumped to out_unlock without clearing the addr_signal flag. This caused mptcp_pm_add_timer to keep rescheduling indefinitely, not sending ADD_ADDR, preventing subsequent addresses in the endpoint list from being announced.

Handle this case by clearing the ADD_ADDR signal and skipping the matching ADD_ADDR retransmission entry. The skip path cancels the matching timer (with id check) and advances PM state progression, preserving forward progress to subsequent PM work.

This cancellation is inherently best-effort. A concurrent add_timer callback may already be running and may acquire pm.lock before the cancel path updates entry state. In that case, one final ADD_ADDR transmit attempt can still be executed.

Once the cancel path sets entry->retrans_times to ADD_ADDR_RETRANS_MAX, the callback-side retrans_times check suppresses further ADD_ADDR retransmissions.

Note that when an ADD_ADDR is being prepared, a pure-ACK is queued. On the output side, it means that it is fine to skip non-pure-ACK packets, when drop_other_suboptions is set: a pure-ACK will be processed soon after.

Stable-dep-of: bd34fa025726 ("mptcp: add-addr: always drop other suboptions")

---
 net/mptcp/mib.c        |  2 ++
 net/mptcp/mib.h        |  6 ++++++
 net/mptcp/pm.c         | 40 +++++++++++++++++++++++++++++++++-------
 net/mptcp/pm_netlink.c | 16 +++++++++++++---
 4 files changed, 54 insertions(+), 10 deletions(-)
net/mptcp/mib.c +2 -0
index fbac6f65270178..4dcd4cf77d7524 100644
@@ -39,7 +39,9 @@ static const struct snmp_mib mptcp_snmp_list[] = {
 	SNMP_MIB_ITEM("NoDSSInWindow", MPTCP_MIB_NODSSWINDOW),
 	SNMP_MIB_ITEM("DuplicateData", MPTCP_MIB_DUPDATA),
 	SNMP_MIB_ITEM("AddAddr", MPTCP_MIB_ADDADDR),
+	SNMP_MIB_ITEM("AddAddrTxDrop", MPTCP_MIB_ADDADDRTXDROP),
 	SNMP_MIB_ITEM("EchoAdd", MPTCP_MIB_ECHOADD),
+	SNMP_MIB_ITEM("EchoAddTxDrop", MPTCP_MIB_ECHOADDTXDROP),
 	SNMP_MIB_ITEM("PortAdd", MPTCP_MIB_PORTADD),
 	SNMP_MIB_ITEM("AddAddrDrop", MPTCP_MIB_ADDADDRDROP),
 	SNMP_MIB_ITEM("MPJoinPortSynRx", MPTCP_MIB_JOINPORTSYNRX),
net/mptcp/mib.h +6 -0
index ff08d41149f431..32944ecf709158 100644
@@ -32,7 +32,13 @@ enum linux_mptcp_mib_field {
 	MPTCP_MIB_NODSSWINDOW,		/* Segments not in MPTCP windows */
 	MPTCP_MIB_DUPDATA,		/* Segments discarded due to duplicate DSS */
 	MPTCP_MIB_ADDADDR,		/* Received ADD_ADDR with echo-flag=0 */
+	MPTCP_MIB_ADDADDRTXDROP,	/* ADD_ADDR with echo-flag=0 not send due to
+					 * resource exhaustion
+					 */
 	MPTCP_MIB_ECHOADD,		/* Received ADD_ADDR with echo-flag=1 */
+	MPTCP_MIB_ECHOADDTXDROP,	/* ADD_ADDR with echo-flag=1 not send due
+					 * to resource exhaustion
+					 */
 	MPTCP_MIB_PORTADD,		/* Received ADD_ADDR with a port-number */
 	MPTCP_MIB_ADDADDRDROP,		/* Dropped incoming ADD_ADDR */
 	MPTCP_MIB_JOINPORTSYNRX,	/* Received a SYN MP_JOIN with a different port-number */
net/mptcp/pm.c +33 -7
index c5131529e15871..80de3e8df5cfcb 100644
@@ -340,6 +340,7 @@ bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, const struct sk_buff *skb,
 			      struct mptcp_addr_info *addr, bool *echo,
 			      bool *drop_other_suboptions)
 {
+	bool skip_add_addr = false;
 	int ret = false;
 	u8 add_addr;
 	u8 family;
@@ -361,24 +362,49 @@ bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, const struct sk_buff *skb,
 	}
 
 	*echo = mptcp_pm_should_add_signal_echo(msk);
-	port = !!(*echo ? msk->pm.remote.port : msk->pm.local.port);
-
-	family = *echo ? msk->pm.remote.family : msk->pm.local.family;
-	if (remaining < mptcp_add_addr_len(family, *echo, port))
-		goto out_unlock;
-
 	if (*echo) {
 		*addr = msk->pm.remote;
 		add_addr = msk->pm.addr_signal & ~BIT(MPTCP_ADD_ADDR_ECHO);
+		port = !!msk->pm.remote.port;
+		family = msk->pm.remote.family;
 	} else {
 		*addr = msk->pm.local;
 		add_addr = msk->pm.addr_signal & ~BIT(MPTCP_ADD_ADDR_SIGNAL);
+		port = !!msk->pm.local.port;
+		family = msk->pm.local.family;
 	}
-	WRITE_ONCE(msk->pm.addr_signal, add_addr);
+
+	if (remaining < mptcp_add_addr_len(family, *echo, port)) {
+		struct net *net = sock_net((struct sock *)msk);
+
+		if (!*drop_other_suboptions)
+			goto out_unlock;
+
+		if (*echo) {
+			MPTCP_INC_STATS(net, MPTCP_MIB_ECHOADDTXDROP);
+		} else {
+			skip_add_addr = true;
+			MPTCP_INC_STATS(net, MPTCP_MIB_ADDADDRTXDROP);
+		}
+		goto drop_signal_mark;
+	}
+
 	ret = true;
 
+drop_signal_mark:
+	WRITE_ONCE(msk->pm.addr_signal, add_addr);
+
 out_unlock:
 	spin_unlock_bh(&msk->pm.lock);
+
+	/* On pure-ACK option-space exhaustion, stop retrying this ADD_ADDR:
+	 * clear the signal bit, cancel the matching retransmission timer, and
+	 * let the PM state machine progress.
+	 */
+	if (skip_add_addr) {
+		mptcp_pm_del_add_timer(msk, addr, true);
+		mptcp_pm_subflow_established(msk);
+	}
 	return ret;
 }
 
net/mptcp/pm_netlink.c +13 -3
index a16a7a538c4255..668a4b01c13c49 100644
@@ -329,7 +329,13 @@ static void mptcp_pm_add_timer(struct timer_list *timer)
 
 	spin_lock_bh(&msk->pm.lock);
 
-	if (!mptcp_pm_should_add_signal_addr(msk)) {
+	/* The cancel path (mptcp_pm_del_add_timer()) can race with this
+	 * callback. Once cancel updates retrans_times to MAX, suppress further
+	 * retransmissions here. If this callback acquires pm.lock first, one
+	 * final transmit attempt is still possible.
+	 */
+	if (entry->retrans_times < ADD_ADDR_RETRANS_MAX &&
+	    !mptcp_pm_should_add_signal_addr(msk)) {
 		pr_debug("retransmit ADD_ADDR id=%d\n", entry->addr.id);
 		mptcp_pm_announce_addr(msk, &entry->addr, false);
 		mptcp_pm_add_addr_send_ack(msk);
@@ -372,8 +378,12 @@ mptcp_pm_del_add_timer(struct mptcp_sock *msk,
 	/* Note: entry might have been removed by another thread.
 	 * We hold rcu_read_lock() to ensure it is not freed under us.
 	 */
-	if (stop_timer)
-		sk_stop_timer_sync(sk, &entry->add_timer);
+	if (stop_timer) {
+		if (check_id)
+			sk_stop_timer(sk, &entry->add_timer);
+		else
+			sk_stop_timer_sync(sk, &entry->add_timer);
+	}
 
 	rcu_read_unlock();
 	return entry;
Signature · 1 line
2.53.0
maintainer
#2 lore raw

PATCH 2/2 mptcp: add-addr: always drop other suboptions

From: "Matthieu Baerts (NGI0)" <[email protected]>

[ Upstream commit bd34fa0257261b76964df1c98f44b3cb4ee14620 ]

When an ADD_ADDR needs to be sent, it could be prepared if there is enough remaining space and even if the packet is not a pure ACK. But it would be dropped soon after.

Indeed, in mptcp_pm_add_addr_signal(), there is enough space to fit a DSS of 20 octets and an ADD_ADDR echo containing an IPv4 address on 8 octets for example. In this case, the packet would be prepared, the MPTCP_ADD_ADDR_ECHO bit would be removed from pm->addr_signal, but the option would be silently dropped in mptcp_established_options_add_addr() not to override DSS info in the union from 'struct mptcp_out_options', and also because mptcp_write_options() will enforce mutually exclusion with DSS.

Instead, don't even try to send an ADD_ADDR if it is not a pure ACK. Retry for each new packet until a pure-ACK is emitted. That's fine to do that, because each time an ADD_ADDR (echo) is scheduled, a pure ACK is queued.

This also simplifies the code, and the skb checks can be done earlier, before the lock.

Note: also, since commit 6d0060f600ad ("mptcp: Write MPTCP DSS headers to outgoing data packets"), opts->ahmac would not have been set to 0 when other suboptions were not dropped, and when sending an ADD_ADDR echo. That would have resulted in sending an ADD_ADDR using garbage info, where there was not enough space, instead of an echo one without the ADD_ADDR HMAC.

---
 net/mptcp/options.c  | 31 ++++++++-----------------------
 net/mptcp/pm.c       | 15 ++++-----------
 net/mptcp/protocol.h |  7 +++----
 3 files changed, 15 insertions(+), 38 deletions(-)
net/mptcp/options.c +8 -23
index eab815d42ac6ae..8e2539b20ba8ca 100644
@@ -657,7 +657,6 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff *
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
 	struct mptcp_sock *msk = mptcp_sk(subflow->conn);
-	bool drop_other_suboptions = false;
 	unsigned int opt_size = *size;
 	struct mptcp_addr_info addr;
 	bool echo;
@@ -668,42 +667,28 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff *
 	 */
 	if (!mptcp_pm_should_add_signal(msk) ||
 	    (opts->suboptions & (OPTION_MPTCP_MPJ_ACK | OPTION_MPTCP_MPC_ACK)) ||
-	    !mptcp_pm_add_addr_signal(msk, skb, opt_size, remaining, &addr,
-		    &echo, &drop_other_suboptions))
+	    !skb || !skb_is_tcp_pure_ack(skb) ||
+	    !mptcp_pm_add_addr_signal(msk, opt_size, remaining, &addr, &echo))
 		return false;
 
-	/*
-	 * Later on, mptcp_write_options() will enforce mutually exclusion with
-	 * DSS, bail out if such option is set and we can't drop it.
-	 */
-	if (drop_other_suboptions)
-		remaining += opt_size;
-	else if (opts->suboptions & OPTION_MPTCP_DSS)
-		return false;
+	remaining += opt_size;
 
 	len = mptcp_add_addr_len(addr.family, echo, !!addr.port);
 	if (remaining < len)
 		return false;
 
 	*size = len;
-	if (drop_other_suboptions) {
-		pr_debug("drop other suboptions\n");
-		opts->suboptions = 0;
-
-		/* note that e.g. DSS could have written into the memory
-		 * aliased by ahmac, we must reset the field here
-		 * to avoid appending the hmac even for ADD_ADDR echo
-		 * options
-		 */
-		opts->ahmac = 0;
-		*size -= opt_size;
-	}
+	pr_debug("drop other suboptions\n");
+	opts->suboptions = 0;
+	*size -= opt_size;
 	opts->addr = addr;
 	opts->suboptions |= OPTION_MPTCP_ADD_ADDR;
 	if (!echo) {
 		opts->ahmac = add_addr_generate_hmac(msk->local_key,
 						     msk->remote_key,
 						     &opts->addr);
+	} else {
+		opts->ahmac = 0;
 	}
 	pr_debug("addr_id=%d, ahmac=%llu, echo=%d, port=%d\n",
 		 opts->addr.id, opts->ahmac, echo, ntohs(opts->addr.port));
net/mptcp/pm.c +4 -11
index 80de3e8df5cfcb..e4cf9d9cca1cda 100644
@@ -335,10 +335,9 @@ void mptcp_pm_mp_fail_received(struct sock *sk, u64 fail_seq)
 
 /* path manager helpers */
 
-bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, const struct sk_buff *skb,
-			      unsigned int opt_size, unsigned int remaining,
-			      struct mptcp_addr_info *addr, bool *echo,
-			      bool *drop_other_suboptions)
+bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, unsigned int opt_size,
+			      unsigned int remaining,
+			      struct mptcp_addr_info *addr, bool *echo)
 {
 	bool skip_add_addr = false;
 	int ret = false;
@@ -356,10 +355,7 @@ bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, const struct sk_buff *skb,
 	 * plain dup-ack from TCP perspective. The other MPTCP-relevant info,
 	 * if any, will be carried by the 'original' TCP ack
 	 */
-	if (skb && skb_is_tcp_pure_ack(skb)) {
-		remaining += opt_size;
-		*drop_other_suboptions = true;
-	}
+	remaining += opt_size;
 
 	*echo = mptcp_pm_should_add_signal_echo(msk);
 	if (*echo) {
@@ -377,9 +373,6 @@ bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, const struct sk_buff *skb,
 	if (remaining < mptcp_add_addr_len(family, *echo, port)) {
 		struct net *net = sock_net((struct sock *)msk);
 
-		if (!*drop_other_suboptions)
-			goto out_unlock;
-
 		if (*echo) {
 			MPTCP_INC_STATS(net, MPTCP_MIB_ECHOADDTXDROP);
 		} else {
net/mptcp/protocol.h +3 -4
index fb3e6ac71bd36f..3e175b917fbb83 100644
@@ -920,10 +920,9 @@ static inline int mptcp_rm_addr_len(const struct mptcp_rm_list *rm_list)
 	return TCPOLEN_MPTCP_RM_ADDR_BASE + roundup(rm_list->nr - 1, 4) + 1;
 }
 
-bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, const struct sk_buff *skb,
-			      unsigned int opt_size, unsigned int remaining,
-			      struct mptcp_addr_info *addr, bool *echo,
-			      bool *drop_other_suboptions);
+bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, unsigned int opt_size,
+			      unsigned int remaining,
+			      struct mptcp_addr_info *addr, bool *echo);
 bool mptcp_pm_rm_addr_signal(struct mptcp_sock *msk, unsigned int remaining,
 			     struct mptcp_rm_list *rm_list);
 int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc);
Signature · 1 line
2.53.0