mptcp: pm: kernel: allow flushing more than 8 endpoints

The mptcp_rm_list structure contains an array of IDs of 8 entries: to be
able to send a RM_ADDR with 8 IDs. This limitation was OK so far because
there could maximum 8 endpoints.

But this is going to change in the next commit. To cope with that, if
one of the arrays is full, the iteration stops, the lists are processed,
then the iteration continues where it previously stopped.

Note that if there are many endpoints to remove, and multiple RM_ADDR to
send, it might be more likely that some of these RM_ADDRs are dropped or
lost. This is a known limitation: RM_ADDR are not retransmitted in
MPTCPv1.

Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20260508-net-next-mptcp-pm-inc-limits-v1-3-c84e3fdf9b6a@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 27 insertions, 11 deletions

diff --git a/net/mptcp/pm_kernel.c b/net/mptcp/pm_kernel.c
index aabd73d15c15..ea3a7ea82013 100644
--- a/net/mptcp/pm_kernel.c
+++ b/net/mptcp/pm_kernel.c
@@ -1223,19 +1223,30 @@ int mptcp_pm_nl_del_addr_doit(struct sk_buff *skb, struct genl_info *info)
 }
 
 static void mptcp_pm_flush_addrs_and_subflows(struct mptcp_sock *msk,
-					      struct list_head *rm_list)
+					      struct list_head *rm_list,
+					      struct mptcp_pm_addr_entry *entry)
 {
-	struct mptcp_rm_list alist = { .nr = 0 }, slist = { .nr = 0 };
-	struct mptcp_pm_addr_entry *entry;
+	struct mptcp_rm_list alist, slist;
+	bool more;
+
+again:
+	alist.nr = 0;
+	slist.nr = 0;
+	more = false;
 
-	list_for_each_entry(entry, rm_list, list) {
-		if (slist.nr < MPTCP_RM_IDS_MAX &&
-		    mptcp_lookup_subflow_by_saddr(&msk->conn_list, &entry->addr))
+	entry = list_prepare_entry(entry, rm_list, list);
+	list_for_each_entry_continue(entry, rm_list, list) {
+		if (mptcp_lookup_subflow_by_saddr(&msk->conn_list, &entry->addr))
 			slist.ids[slist.nr++] = mptcp_endp_get_local_id(msk, &entry->addr);
 
-		if (alist.nr < MPTCP_RM_IDS_MAX &&
-		    mptcp_remove_anno_list_by_saddr(msk, &entry->addr))
+		if (mptcp_remove_anno_list_by_saddr(msk, &entry->addr))
 			alist.ids[alist.nr++] = mptcp_endp_get_local_id(msk, &entry->addr);
+
+		if (slist.nr == MPTCP_RM_IDS_MAX ||
+		    alist.nr == MPTCP_RM_IDS_MAX) {
+			more = !list_is_last(&entry->list, rm_list);
+			break;
+		}
 	}
 
 	spin_lock_bh(&msk->pm.lock);
@@ -1246,9 +1257,14 @@ static void mptcp_pm_flush_addrs_and_subflows(struct mptcp_sock *msk,
 	if (slist.nr)
 		mptcp_pm_rm_subflow(msk, &slist);
 	/* Reset counters: maybe some subflows have been removed before */
-	bitmap_fill(msk->pm.id_avail_bitmap, MPTCP_PM_MAX_ADDR_ID + 1);
-	msk->pm.local_addr_used = 0;
+	if (!more) {
+		bitmap_fill(msk->pm.id_avail_bitmap, MPTCP_PM_MAX_ADDR_ID + 1);
+		msk->pm.local_addr_used = 0;
+	}
 	spin_unlock_bh(&msk->pm.lock);
+
+	if (more)
+		goto again;
 }
 
 static void mptcp_nl_flush_addrs_list(struct net *net,
@@ -1265,7 +1281,7 @@ static void mptcp_nl_flush_addrs_list(struct net *net,
 
 		if (!mptcp_pm_is_userspace(msk)) {
 			lock_sock(sk);
-			mptcp_pm_flush_addrs_and_subflows(msk, rm_list);
+			mptcp_pm_flush_addrs_and_subflows(msk, rm_list, NULL);
 			release_sock(sk);
 		}