Merge branch 'mptcp-misc-fixes-for-v7-0-rc2'

Matthieu Baerts says:

====================
mptcp: misc fixes for v7.0-rc2

Here are various unrelated fixes:

- Patch 1: avoid bufferbloat in simult_flows selftest which can cause
  instabilities. A fix for v5.10.

- Patches 2-3: reduce RM_ADDR lost by not sending it over the same
  subflow as the one being removed, if possible. A fix for v5.13.

- Patches 4-5: avoid a WARN when using signal + subflow endpoints with a
  subflow limit of 0, and removing such endpoints during an active
  connection. A fix for v5.17.
====================

Link: https://patch.msgid.link/20260303-net-mptcp-misc-fixes-7-0-rc2-v1-0-4b5462b6f016@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

4 files changed, 108 insertions, 16 deletions

diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index 7298836469b3..57a456690406 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -212,9 +212,24 @@ void mptcp_pm_send_ack(struct mptcp_sock *msk,
 	spin_lock_bh(&msk->pm.lock);
 }
 
-void mptcp_pm_addr_send_ack(struct mptcp_sock *msk)
+static bool subflow_in_rm_list(const struct mptcp_subflow_context *subflow,
+			       const struct mptcp_rm_list *rm_list)
+{
+	u8 i, id = subflow_get_local_id(subflow);
+
+	for (i = 0; i < rm_list->nr; i++) {
+		if (rm_list->ids[i] == id)
+			return true;
+	}
+
+	return false;
+}
+
+static void
+mptcp_pm_addr_send_ack_avoid_list(struct mptcp_sock *msk,
+				  const struct mptcp_rm_list *rm_list)
 {
-	struct mptcp_subflow_context *subflow, *alt = NULL;
+	struct mptcp_subflow_context *subflow, *stale = NULL, *same_id = NULL;
 
 	msk_owned_by_me(msk);
 	lockdep_assert_held(&msk->pm.lock);
@@ -224,19 +239,35 @@ void mptcp_pm_addr_send_ack(struct mptcp_sock *msk)
 		return;
 
 	mptcp_for_each_subflow(msk, subflow) {
-		if (__mptcp_subflow_active(subflow)) {
-			if (!subflow->stale) {
-				mptcp_pm_send_ack(msk, subflow, false, false);
-				return;
-			}
+		if (!__mptcp_subflow_active(subflow))
+			continue;
 
-			if (!alt)
-				alt = subflow;
+		if (unlikely(subflow->stale)) {
+			if (!stale)
+				stale = subflow;
+		} else if (unlikely(rm_list &&
+				    subflow_in_rm_list(subflow, rm_list))) {
+			if (!same_id)
+				same_id = subflow;
+		} else {
+			goto send_ack;
 		}
 	}
 
-	if (alt)
-		mptcp_pm_send_ack(msk, alt, false, false);
+	if (same_id)
+		subflow = same_id;
+	else if (stale)
+		subflow = stale;
+	else
+		return;
+
+send_ack:
+	mptcp_pm_send_ack(msk, subflow, false, false);
+}
+
+void mptcp_pm_addr_send_ack(struct mptcp_sock *msk)
+{
+	mptcp_pm_addr_send_ack_avoid_list(msk, NULL);
 }
 
 int mptcp_pm_mp_prio_send_ack(struct mptcp_sock *msk,
@@ -470,7 +501,7 @@ int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_
 	msk->pm.rm_list_tx = *rm_list;
 	rm_addr |= BIT(MPTCP_RM_ADDR_SIGNAL);
 	WRITE_ONCE(msk->pm.addr_signal, rm_addr);
-	mptcp_pm_addr_send_ack(msk);
+	mptcp_pm_addr_send_ack_avoid_list(msk, rm_list);
 	return 0;
 }
 
diff --git a/net/mptcp/pm_kernel.c b/net/mptcp/pm_kernel.c
index b5316a6c7d1b..b2b9df43960e 100644
--- a/net/mptcp/pm_kernel.c
+++ b/net/mptcp/pm_kernel.c
@@ -418,6 +418,15 @@ subflow:
 	}
 
 exit:
+	/* If an endpoint has both the signal and subflow flags, but it is not
+	 * possible to create subflows -- the 'while' loop body above never
+	 * executed --  then still mark the endp as used, which is somehow the
+	 * case. This avoids issues later when removing the endpoint and calling
+	 * __mark_subflow_endp_available(), which expects the increment here.
+	 */
+	if (signal_and_subflow && local.addr.id != msk->mpc_endpoint_id)
+		msk->pm.local_addr_used++;
+
 	mptcp_pm_nl_check_work_pending(msk);
 }
 
diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index dc1f200aaa81..a3144d7298a5 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -104,6 +104,24 @@ CBPF_MPTCP_SUBOPTION_ADD_ADDR="14,
 			       6 0 0 65535,
 			       6 0 0 0"
 
+# IPv4: TCP hdr of 48B, a first suboption of 12B (DACK8), the RM_ADDR suboption
+# generated using "nfbpf_compile '(ip[32] & 0xf0) == 0xc0 && ip[53] == 0x0c &&
+#				  (ip[66] & 0xf0) == 0x40'"
+CBPF_MPTCP_SUBOPTION_RM_ADDR="13,
+			      48 0 0 0,
+			      84 0 0 240,
+			      21 0 9 64,
+			      48 0 0 32,
+			      84 0 0 240,
+			      21 0 6 192,
+			      48 0 0 53,
+			      21 0 4 12,
+			      48 0 0 66,
+			      84 0 0 240,
+			      21 0 1 64,
+			      6 0 0 65535,
+			      6 0 0 0"
+
 init_partial()
 {
 	capout=$(mktemp)
@@ -2608,6 +2626,19 @@ remove_tests()
 		chk_rst_nr 0 0
 	fi
 
+	# signal+subflow with limits, remove
+	if reset "remove signal+subflow with limits"; then
+		pm_nl_set_limits $ns1 0 0
+		pm_nl_add_endpoint $ns1 10.0.2.1 flags signal,subflow
+		pm_nl_set_limits $ns2 0 0
+		addr_nr_ns1=-1 speed=slow \
+			run_tests $ns1 $ns2 10.0.1.1
+		chk_join_nr 0 0 0
+		chk_add_nr 1 1
+		chk_rm_nr 1 0 invert
+		chk_rst_nr 0 0
+	fi
+
 	# addresses remove
 	if reset "remove addresses"; then
 		pm_nl_set_limits $ns1 3 3
@@ -4217,6 +4248,14 @@ endpoint_tests()
 		chk_subflow_nr "after no reject" 3
 		chk_mptcp_info subflows 2 subflows 2
 
+		# To make sure RM_ADDR are sent over a different subflow, but
+		# allow the rest to quickly and cleanly close the subflow
+		local ipt=1
+		ip netns exec "${ns2}" ${iptables} -I OUTPUT -s "10.0.1.2" \
+			-p tcp -m tcp --tcp-option 30 \
+			-m bpf --bytecode \
+			"$CBPF_MPTCP_SUBOPTION_RM_ADDR" \
+			-j DROP || ipt=0
 		local i
 		for i in $(seq 3); do
 			pm_nl_del_endpoint $ns2 1 10.0.1.2
@@ -4229,6 +4268,7 @@ endpoint_tests()
 			chk_subflow_nr "after re-add id 0 ($i)" 3
 			chk_mptcp_info subflows 3 subflows 3
 		done
+		[ ${ipt} = 1 ] && ip netns exec "${ns2}" ${iptables} -D OUTPUT 1
 
 		mptcp_lib_kill_group_wait $tests_pid
 
@@ -4288,11 +4328,20 @@ endpoint_tests()
 		chk_mptcp_info subflows 2 subflows 2
 		chk_mptcp_info add_addr_signal 2 add_addr_accepted 2
 
+		# To make sure RM_ADDR are sent over a different subflow, but
+		# allow the rest to quickly and cleanly close the subflow
+		local ipt=1
+		ip netns exec "${ns1}" ${iptables} -I OUTPUT -s "10.0.1.1" \
+			-p tcp -m tcp --tcp-option 30 \
+			-m bpf --bytecode \
+			"$CBPF_MPTCP_SUBOPTION_RM_ADDR" \
+			-j DROP || ipt=0
 		pm_nl_del_endpoint $ns1 42 10.0.1.1
 		sleep 0.5
 		chk_subflow_nr "after delete ID 0" 2
 		chk_mptcp_info subflows 2 subflows 2
 		chk_mptcp_info add_addr_signal 2 add_addr_accepted 2
+		[ ${ipt} = 1 ] && ip netns exec "${ns1}" ${iptables} -D OUTPUT 1
 
 		pm_nl_add_endpoint $ns1 10.0.1.1 id 99 flags signal
 		wait_mpj 4
diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh
index 806aaa7d2d61..d11a8b949aab 100755
--- a/tools/testing/selftests/net/mptcp/simult_flows.sh
+++ b/tools/testing/selftests/net/mptcp/simult_flows.sh
@@ -237,10 +237,13 @@ run_test()
 	for dev in ns2eth1 ns2eth2; do
 		tc -n $ns2 qdisc del dev $dev root >/dev/null 2>&1
 	done
-	tc -n $ns1 qdisc add dev ns1eth1 root netem rate ${rate1}mbit $delay1
-	tc -n $ns1 qdisc add dev ns1eth2 root netem rate ${rate2}mbit $delay2
-	tc -n $ns2 qdisc add dev ns2eth1 root netem rate ${rate1}mbit $delay1
-	tc -n $ns2 qdisc add dev ns2eth2 root netem rate ${rate2}mbit $delay2
+
+	# keep the queued pkts number low, or the RTT estimator will see
+	# increasing latency over time.
+	tc -n $ns1 qdisc add dev ns1eth1 root netem rate ${rate1}mbit $delay1 limit 50
+	tc -n $ns1 qdisc add dev ns1eth2 root netem rate ${rate2}mbit $delay2 limit 50
+	tc -n $ns2 qdisc add dev ns2eth1 root netem rate ${rate1}mbit $delay1 limit 50
+	tc -n $ns2 qdisc add dev ns2eth2 root netem rate ${rate2}mbit $delay2 limit 50
 
 	# time is measured in ms, account for transfer size, aggregated link speed
 	# and header overhead (10%)