diff mbox series

[net-next,1/8] mptcp: let the in-kernel PM use mixed IPv4 and IPv6 addresses

Message ID 20230123-upstream-net-next-pm-v4-v6-v1-1-43fac502bfbf@tessares.net
State New
Headers show
Series mptcp: add mixed v4/v6 support for the in-kernel PM | expand

Commit Message

Matthieu Baerts Jan. 25, 2023, 10:47 a.m. UTC
From: Paolo Abeni <pabeni@redhat.com>

Currently the in-kernel PM arbitrary enforces that created subflow's
family must match the main MPTCP socket while the RFC allows mixing
IPv4 and IPv6 subflows.

This patch changes the in-kernel PM logic to create subflows matching
the currently selected source (or destination) address. IPv4 sockets
can pick only IPv4 addresses (and v4 mapped in v6), while IPv6 sockets
not restricted to V6ONLY can pick either IPv4 and IPv6 addresses as
long as the source and destination matches.

A helper, previously introduced is used to ease family matching checks,
taking care of IPv4 vs IPv4-mapped-IPv6 vs IPv6 only addresses.

Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/269
Co-developed-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
---
 net/mptcp/pm_netlink.c | 58 +++++++++++++++++++++++++++-----------------------
 1 file changed, 31 insertions(+), 27 deletions(-)
diff mbox series

Patch

diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index b5505b8167f9..db07cc5b4fcb 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -152,7 +152,6 @@  static struct mptcp_pm_addr_entry *
 select_local_address(const struct pm_nl_pernet *pernet,
 		     const struct mptcp_sock *msk)
 {
-	const struct sock *sk = (const struct sock *)msk;
 	struct mptcp_pm_addr_entry *entry, *ret = NULL;
 
 	msk_owned_by_me(msk);
@@ -165,16 +164,6 @@  select_local_address(const struct pm_nl_pernet *pernet,
 		if (!test_bit(entry->addr.id, msk->pm.id_avail_bitmap))
 			continue;
 
-		if (entry->addr.family != sk->sk_family) {
-#if IS_ENABLED(CONFIG_MPTCP_IPV6)
-			if ((entry->addr.family == AF_INET &&
-			     !ipv6_addr_v4mapped(&sk->sk_v6_daddr)) ||
-			    (sk->sk_family == AF_INET &&
-			     !ipv6_addr_v4mapped(&entry->addr.addr6)))
-#endif
-				continue;
-		}
-
 		ret = entry;
 		break;
 	}
@@ -423,7 +412,9 @@  static bool lookup_address_in_vec(const struct mptcp_addr_info *addrs, unsigned
 /* Fill all the remote addresses into the array addrs[],
  * and return the array size.
  */
-static unsigned int fill_remote_addresses_vec(struct mptcp_sock *msk, bool fullmesh,
+static unsigned int fill_remote_addresses_vec(struct mptcp_sock *msk,
+					      struct mptcp_addr_info *local,
+					      bool fullmesh,
 					      struct mptcp_addr_info *addrs)
 {
 	bool deny_id0 = READ_ONCE(msk->pm.remote_deny_join_id0);
@@ -443,6 +434,9 @@  static unsigned int fill_remote_addresses_vec(struct mptcp_sock *msk, bool fullm
 		if (deny_id0)
 			return 0;
 
+		if (!mptcp_pm_addr_families_match(sk, local, &remote))
+			return 0;
+
 		msk->pm.subflows++;
 		addrs[i++] = remote;
 	} else {
@@ -453,6 +447,9 @@  static unsigned int fill_remote_addresses_vec(struct mptcp_sock *msk, bool fullm
 			if (deny_id0 && !addrs[i].id)
 				continue;
 
+			if (!mptcp_pm_addr_families_match(sk, local, &addrs[i]))
+				continue;
+
 			if (!lookup_address_in_vec(addrs, i, &addrs[i]) &&
 			    msk->pm.subflows < subflows_max) {
 				msk->pm.subflows++;
@@ -603,9 +600,11 @@  static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
 		fullmesh = !!(local->flags & MPTCP_PM_ADDR_FLAG_FULLMESH);
 
 		msk->pm.local_addr_used++;
-		nr = fill_remote_addresses_vec(msk, fullmesh, addrs);
-		if (nr)
-			__clear_bit(local->addr.id, msk->pm.id_avail_bitmap);
+		__clear_bit(local->addr.id, msk->pm.id_avail_bitmap);
+		nr = fill_remote_addresses_vec(msk, &local->addr, fullmesh, addrs);
+		if (nr == 0)
+			continue;
+
 		spin_unlock_bh(&msk->pm.lock);
 		for (i = 0; i < nr; i++)
 			__mptcp_subflow_connect(sk, &local->addr, &addrs[i]);
@@ -628,11 +627,11 @@  static void mptcp_pm_nl_subflow_established(struct mptcp_sock *msk)
  * and return the array size.
  */
 static unsigned int fill_local_addresses_vec(struct mptcp_sock *msk,
+					     struct mptcp_addr_info *remote,
 					     struct mptcp_addr_info *addrs)
 {
 	struct sock *sk = (struct sock *)msk;
 	struct mptcp_pm_addr_entry *entry;
-	struct mptcp_addr_info local;
 	struct pm_nl_pernet *pernet;
 	unsigned int subflows_max;
 	int i = 0;
@@ -645,15 +644,8 @@  static unsigned int fill_local_addresses_vec(struct mptcp_sock *msk,
 		if (!(entry->flags & MPTCP_PM_ADDR_FLAG_FULLMESH))
 			continue;
 
-		if (entry->addr.family != sk->sk_family) {
-#if IS_ENABLED(CONFIG_MPTCP_IPV6)
-			if ((entry->addr.family == AF_INET &&
-			     !ipv6_addr_v4mapped(&sk->sk_v6_daddr)) ||
-			    (sk->sk_family == AF_INET &&
-			     !ipv6_addr_v4mapped(&entry->addr.addr6)))
-#endif
-				continue;
-		}
+		if (!mptcp_pm_addr_families_match(sk, &entry->addr, remote))
+			continue;
 
 		if (msk->pm.subflows < subflows_max) {
 			msk->pm.subflows++;
@@ -666,8 +658,18 @@  static unsigned int fill_local_addresses_vec(struct mptcp_sock *msk,
 	 * 'IPADDRANY' local address
 	 */
 	if (!i) {
+		struct mptcp_addr_info local;
+
 		memset(&local, 0, sizeof(local));
-		local.family = msk->pm.remote.family;
+		local.family =
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+			       remote->family == AF_INET6 &&
+			       ipv6_addr_v4mapped(&remote->addr6) ? AF_INET :
+#endif
+			       remote->family;
+
+		if (!mptcp_pm_addr_families_match(sk, &local, remote))
+			return 0;
 
 		msk->pm.subflows++;
 		addrs[i++] = local;
@@ -706,7 +708,9 @@  static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk)
 	/* connect to the specified remote address, using whatever
 	 * local address the routing configuration will pick.
 	 */
-	nr = fill_local_addresses_vec(msk, addrs);
+	nr = fill_local_addresses_vec(msk, &remote, addrs);
+	if (nr == 0)
+		return;
 
 	msk->pm.add_addr_accepted++;
 	if (msk->pm.add_addr_accepted >= add_addr_accept_max ||