Merge branch 'mptcp-pm-misc-fixes-for-v7-1-rc3'

Matthieu Baerts says:

====================
mptcp: pm: misc. fixes for v7.1-rc3

Here are various fixes, mainly related to ADD_ADDRs:

- Patch 1: save ADD_ADDR for rtx with ID0 when needed. A fix for v6.1.

- Patch 2: remove unneeded exception for ID 0. A fix for v5.10.

- Patches 3-5: fix potential data-race and leaks during ADD_ADDR rtx. A
  fix for v5.10.

- Patch 6: resched blocked ADD_ADDR rtx after a more appropriated
  timeout, not after 15 seconds. A fix for v5.10.

- Patch 7: skip inactive subflows when when looking at the max RTO. A
  fix for v6.18.

- Patch 8: avoid iterating over all subflows when there is no need to. A
  fix for v6.18.

- Patch 9: skip closed subflows when looking at sending MP_PRIO. A fix
  for v5.17.

- Patch 10: properly catch errors when using check_output() in the
  selftests. A fix for v6.9.

- Patch 11: skip the 'unknown' flag test when 'ip mptcp' is used. A fix
  for v6.10.
====================

Link: https://patch.msgid.link/20260505-net-mptcp-pm-fixes-7-1-rc3-v1-0-fca8091060a4@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

4 files changed, 73 insertions, 38 deletions

diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index 57a456690406..3c152bf66cd5 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -16,6 +16,7 @@ struct mptcp_pm_add_entry {
 	struct list_head	list;
 	struct mptcp_addr_info	addr;
 	u8			retrans_times;
+	bool			timer_done;
 	struct timer_list	add_timer;
 	struct mptcp_sock	*sock;
 	struct rcu_head		rcu;
@@ -283,6 +284,9 @@ int mptcp_pm_mp_prio_send_ack(struct mptcp_sock *msk,
 		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
 		struct mptcp_addr_info local, remote;
 
+		if (!__mptcp_subflow_active(subflow))
+			continue;
+
 		mptcp_local_address((struct sock_common *)ssk, &local);
 		if (!mptcp_addresses_equal(&local, addr, addr->port))
 			continue;
@@ -305,18 +309,31 @@ static unsigned int mptcp_adjust_add_addr_timeout(struct mptcp_sock *msk)
 	const struct net *net = sock_net((struct sock *)msk);
 	unsigned int rto = mptcp_get_add_addr_timeout(net);
 	struct mptcp_subflow_context *subflow;
-	unsigned int max = 0;
+	unsigned int max = 0, max_stale = 0;
+
+	if (!rto)
+		return 0;
 
 	mptcp_for_each_subflow(msk, subflow) {
 		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
 		struct inet_connection_sock *icsk = inet_csk(ssk);
 
-		if (icsk->icsk_rto > max)
+		if (!__mptcp_subflow_active(subflow))
+			continue;
+
+		if (unlikely(subflow->stale)) {
+			if (icsk->icsk_rto > max_stale)
+				max_stale = icsk->icsk_rto;
+		} else if (icsk->icsk_rto > max) {
 			max = icsk->icsk_rto;
+		}
 	}
 
-	if (max && max < rto)
-		rto = max;
+	if (max)
+		return min(max, rto);
+
+	if (max_stale)
+		return min(max_stale, rto);
 
 	return rto;
 }
@@ -327,26 +344,22 @@ static void mptcp_pm_add_timer(struct timer_list *timer)
 							      add_timer);
 	struct mptcp_sock *msk = entry->sock;
 	struct sock *sk = (struct sock *)msk;
-	unsigned int timeout;
+	unsigned int timeout = 0;
 
 	pr_debug("msk=%p\n", msk);
 
-	if (!msk)
-		return;
-
-	if (inet_sk_state_load(sk) == TCP_CLOSE)
-		return;
-
-	if (!entry->addr.id)
-		return;
+	bh_lock_sock(sk);
+	if (unlikely(inet_sk_state_load(sk) == TCP_CLOSE))
+		goto out;
 
-	if (mptcp_pm_should_add_signal_addr(msk)) {
-		sk_reset_timer(sk, timer, jiffies + TCP_RTO_MAX / 8);
+	if (sock_owned_by_user(sk)) {
+		/* Try again later. */
+		timeout = HZ / 20;
 		goto out;
 	}
 
 	timeout = mptcp_adjust_add_addr_timeout(msk);
-	if (!timeout)
+	if (!timeout || mptcp_pm_should_add_signal_addr(msk))
 		goto out;
 
 	spin_lock_bh(&msk->pm.lock);
@@ -359,8 +372,9 @@ static void mptcp_pm_add_timer(struct timer_list *timer)
 	}
 
 	if (entry->retrans_times < ADD_ADDR_RETRANS_MAX)
-		sk_reset_timer(sk, timer,
-			       jiffies + (timeout << entry->retrans_times));
+		timeout <<= entry->retrans_times;
+	else
+		timeout = 0;
 
 	spin_unlock_bh(&msk->pm.lock);
 
@@ -368,7 +382,13 @@ static void mptcp_pm_add_timer(struct timer_list *timer)
 		mptcp_pm_subflow_established(msk);
 
 out:
-	__sock_put(sk);
+	if (timeout)
+		sk_reset_timer(sk, timer, jiffies + timeout);
+	else
+		/* if sock_put calls sk_free: avoid waiting for this timer */
+		entry->timer_done = true;
+	bh_unlock_sock(sk);
+	sock_put(sk);
 }
 
 struct mptcp_pm_add_entry *
@@ -431,6 +451,7 @@ bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk,
 
 	timer_setup(&add_entry->add_timer, mptcp_pm_add_timer, 0);
 reset_timer:
+	add_entry->timer_done = false;
 	timeout = mptcp_adjust_add_addr_timeout(msk);
 	if (timeout)
 		sk_reset_timer(sk, &add_entry->add_timer, jiffies + timeout);
@@ -451,7 +472,8 @@ static void mptcp_pm_free_anno_list(struct mptcp_sock *msk)
 	spin_unlock_bh(&msk->pm.lock);
 
 	list_for_each_entry_safe(entry, tmp, &free_list, list) {
-		sk_stop_timer_sync(sk, &entry->add_timer);
+		if (!entry->timer_done)
+			sk_stop_timer_sync(sk, &entry->add_timer);
 		kfree_rcu(entry, rcu);
 	}
 }
diff --git a/net/mptcp/pm_kernel.c b/net/mptcp/pm_kernel.c
index c9f1e5af3cd3..fc818b63752e 100644
--- a/net/mptcp/pm_kernel.c
+++ b/net/mptcp/pm_kernel.c
@@ -347,6 +347,8 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
 
 	/* check first for announce */
 	if (msk->pm.add_addr_signaled < endp_signal_max) {
+		u8 endp_id;
+
 		/* due to racing events on both ends we can reach here while
 		 * previous add address is still running: if we invoke now
 		 * mptcp_pm_announce_addr(), that will fail and the
@@ -360,19 +362,20 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
 		if (!select_signal_address(pernet, msk, &local))
 			goto subflow;
 
+		/* Special case for ID0: set the correct ID */
+		endp_id = local.addr.id;
+		if (endp_id == msk->mpc_endpoint_id)
+			local.addr.id = 0;
+
 		/* If the alloc fails, we are on memory pressure, not worth
 		 * continuing, and trying to create subflows.
 		 */
 		if (!mptcp_pm_alloc_anno_list(msk, &local.addr))
 			return;
 
-		__clear_bit(local.addr.id, msk->pm.id_avail_bitmap);
+		__clear_bit(endp_id, msk->pm.id_avail_bitmap);
 		msk->pm.add_addr_signaled++;
 
-		/* Special case for ID0: set the correct ID */
-		if (local.addr.id == msk->mpc_endpoint_id)
-			local.addr.id = 0;
-
 		mptcp_pm_announce_addr(msk, &local.addr, false);
 		mptcp_pm_addr_send_ack(msk);
 
diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh
index 5fea7e7df628..989a5975dcea 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh
@@ -474,20 +474,24 @@ mptcp_lib_wait_local_port_listen() {
 	wait_local_port_listen "${@}" "tcp"
 }
 
+# $1: error file, $2: cmd, $3: expected msg, [$4: expected error]
 mptcp_lib_check_output() {
 	local err="${1}"
 	local cmd="${2}"
 	local expected="${3}"
+	local exp_error="${4:-0}"
 	local cmd_ret=0
 	local out
 
-	if ! out=$(${cmd} 2>"${err}"); then
-		cmd_ret=${?}
-	fi
+	out=$(${cmd} 2>"${err}") || cmd_ret=1
 
-	if [ ${cmd_ret} -ne 0 ]; then
-		mptcp_lib_pr_fail "command execution '${cmd}' stderr"
-		cat "${err}"
+	if [ "${cmd_ret}" != "${exp_error}" ]; then
+		mptcp_lib_pr_fail "unexpected returned code for '${cmd}', info:"
+		if [ "${exp_error}" = 0 ]; then
+			cat "${err}"
+		else
+			echo "${out}"
+		fi
 		return 2
 	elif [ "${out}" = "${expected}" ]; then
 		return 0
diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh
index 123d9d7a0278..04594dfc22b1 100755
--- a/tools/testing/selftests/net/mptcp/pm_netlink.sh
+++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh
@@ -122,10 +122,12 @@ check()
 	local cmd="$1"
 	local expected="$2"
 	local msg="$3"
+	local exp_error="$4"
 	local rc=0
 
 	mptcp_lib_print_title "$msg"
-	mptcp_lib_check_output "${err}" "${cmd}" "${expected}" || rc=${?}
+	mptcp_lib_check_output "${err}" "${cmd}" "${expected}" "${exp_error}" ||
+		rc=${?}
 	if [ ${rc} -eq 2 ]; then
 		mptcp_lib_result_fail "${msg} # error ${rc}"
 		ret=${KSFT_FAIL}
@@ -158,13 +160,13 @@ check "show_endpoints" \
 			    "3,10.0.1.3,signal backup")" "dump addrs"
 
 del_endpoint 2
-check "get_endpoint 2" "" "simple del addr"
+check "get_endpoint 2" "" "simple del addr" 1
 check "show_endpoints" \
 	"$(format_endpoints "1,10.0.1.1" \
 			    "3,10.0.1.3,signal backup")" "dump addrs after del"
 
 add_endpoint 10.0.1.3 2>/dev/null
-check "get_endpoint 4" "" "duplicate addr"
+check "get_endpoint 4" "" "duplicate addr" 1
 
 add_endpoint 10.0.1.4 flags signal
 check "get_endpoint 4" "$(format_endpoints "4,10.0.1.4,signal")" "id addr increment"
@@ -173,7 +175,7 @@ for i in $(seq 5 9); do
 	add_endpoint "10.0.1.${i}" flags signal >/dev/null 2>&1
 done
 check "get_endpoint 9" "$(format_endpoints "9,10.0.1.9,signal")" "hard addr limit"
-check "get_endpoint 10" "" "above hard addr limit"
+check "get_endpoint 10" "" "above hard addr limit" 1
 
 del_endpoint 9
 for i in $(seq 10 255); do
@@ -192,9 +194,13 @@ check "show_endpoints" \
 flush_endpoint
 check "show_endpoints" "" "flush addrs"
 
-add_endpoint 10.0.1.1 flags unknown
-check "show_endpoints" "$(format_endpoints "1,10.0.1.1")" "ignore unknown flags"
-flush_endpoint
+# "unknown" flag is only supported by pm_nl_ctl
+if ! mptcp_lib_is_ip_mptcp; then
+	add_endpoint 10.0.1.1 flags unknown
+	check "show_endpoints" "$(format_endpoints "1,10.0.1.1")" \
+	      "ignore unknown flags"
+	flush_endpoint
+fi
 
 set_limits 9 1 2>/dev/null
 check "get_limits" "${default_limits}" "rcv addrs above hard limit"