mptcp: strict local address ID selection

The address ID selection for MPJ subflows created in response
to incoming ADD_ADDR option is currently unreliable: it happens
at MPJ socket creation time, when the local address could be
unknown.

Additionally, if the no local endpoint is available for the local
address, a new dummy endpoint is created, confusing the user-land.

This change refactor the code to move the address ID selection inside
the rebuild_header() helper, when the local address eventually
selected by the route lookup is finally known. If the address used
is not mapped by any endpoint - and thus can't be advertised/removed
pick the id 0 instead of allocate a new endpoint.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 10368a4f1c4a7a4612a958e396b8267fae5a7f88..e090810bb35dec55037e30829795cac578294ee2 100644 (file)
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -83,16 +83,6 @@ static bool addresses_equal(const struct mptcp_addr_info *a,
        return a->port == b->port;
 }
 
-static bool address_zero(const struct mptcp_addr_info *addr)
-{
-       struct mptcp_addr_info zero;
-
-       memset(&zero, 0, sizeof(zero));
-       zero.family = addr->family;
-
-       return addresses_equal(addr, &zero, true);
-}
-
 static void local_address(const struct sock_common *skc,
                          struct mptcp_addr_info *addr)
 {
@@ -1039,9 +1029,6 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc)
        if (addresses_equal(&msk_local, &skc_local, false))
                return 0;
 
-       if (address_zero(&skc_local))
-               return 0;
-
        pernet = net_generic(sock_net((struct sock *)msk), pm_nl_pernet_id);
 
        rcu_read_lock();

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 36a7d33f670a00e4d5346bd97228573fa2863068..101aeebeb9ebbb77805cb316728a217d960996e9 100644 (file)
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -117,6 +117,9 @@ static int __mptcp_socket_create(struct mptcp_sock *msk)
        list_add(&subflow->node, &msk->conn_list);
        sock_hold(ssock->sk);
        subflow->request_mptcp = 1;
+
+       /* This is the first subflow, always with id 0 */
+       subflow->local_id_valid = 1;
        mptcp_sock_graft(msk->first, sk->sk_socket);
 
        return 0;

diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 9d0ee6cee07f67422be0475125ab441e8715fc98..3c1a3036550f8410ba31d4d2c960d27c29c90186 100644 (file)
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -442,7 +442,8 @@ struct mptcp_subflow_context {
                rx_eof : 1,
                can_ack : 1,        /* only after processing the remote a key */
                disposable : 1,     /* ctx can be free at ulp release time */
-               stale : 1;          /* unable to snd/rcv data, do not use for xmit */
+               stale : 1,          /* unable to snd/rcv data, do not use for xmit */
+               local_id_valid : 1; /* local_id is correctly initialized */
        enum mptcp_data_avail data_avail;
        u32     remote_nonce;
        u64     thmac;

diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index bb09a008e733b6b6de3c6c7a22f3177b06ee8536..aba260f547daa1a10f2f5d32294b54b0a1f2e10b 100644 (file)
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -481,6 +481,51 @@ do_reset:
        mptcp_subflow_reset(sk);
 }
 
+static void subflow_set_local_id(struct mptcp_subflow_context *subflow, int local_id)
+{
+       subflow->local_id = local_id;
+       subflow->local_id_valid = 1;
+}
+
+static int subflow_chk_local_id(struct sock *sk)
+{
+       struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
+       struct mptcp_sock *msk = mptcp_sk(subflow->conn);
+       int err;
+
+       if (likely(subflow->local_id_valid))
+               return 0;
+
+       err = mptcp_pm_get_local_id(msk, (struct sock_common *)sk);
+       if (err < 0)
+               return err;
+
+       subflow_set_local_id(subflow, err);
+       return 0;
+}
+
+static int subflow_rebuild_header(struct sock *sk)
+{
+       int err = subflow_chk_local_id(sk);
+
+       if (unlikely(err < 0))
+               return err;
+
+       return inet_sk_rebuild_header(sk);
+}
+
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+static int subflow_v6_rebuild_header(struct sock *sk)
+{
+       int err = subflow_chk_local_id(sk);
+
+       if (unlikely(err < 0))
+               return err;
+
+       return inet6_sk_rebuild_header(sk);
+}
+#endif
+
 struct request_sock_ops mptcp_subflow_request_sock_ops;
 static struct tcp_request_sock_ops subflow_request_sock_ipv4_ops __ro_after_init;
 
@@ -1398,13 +1443,8 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc,
                get_random_bytes(&subflow->local_nonce, sizeof(u32));
        } while (!subflow->local_nonce);
 
-       if (!local_id) {
-               err = mptcp_pm_get_local_id(msk, (struct sock_common *)ssk);
-               if (err < 0)
-                       goto failed;
-
-               local_id = err;
-       }
+       if (local_id)
+               subflow_set_local_id(subflow, local_id);
 
        mptcp_pm_get_flags_and_ifindex_by_id(sock_net(sk), local_id,
                                             &flags, &ifindex);
@@ -1429,7 +1469,6 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc,
        pr_debug("msk=%p remote_token=%u local_id=%d remote_id=%d", msk,
                 remote_token, local_id, remote_id);
        subflow->remote_token = remote_token;
-       subflow->local_id = local_id;
        subflow->remote_id = remote_id;
        subflow->request_join = 1;
        subflow->request_bkup = !!(flags & MPTCP_PM_ADDR_FLAG_BACKUP);
@@ -1728,15 +1767,22 @@ static void subflow_ulp_clone(const struct request_sock *req,
                new_ctx->token = subflow_req->token;
                new_ctx->ssn_offset = subflow_req->ssn_offset;
                new_ctx->idsn = subflow_req->idsn;
+
+               /* this is the first subflow, id is always 0 */
+               new_ctx->local_id_valid = 1;
        } else if (subflow_req->mp_join) {
                new_ctx->ssn_offset = subflow_req->ssn_offset;
                new_ctx->mp_join = 1;
                new_ctx->fully_established = 1;
                new_ctx->backup = subflow_req->backup;
-               new_ctx->local_id = subflow_req->local_id;
                new_ctx->remote_id = subflow_req->remote_id;
                new_ctx->token = subflow_req->token;
                new_ctx->thmac = subflow_req->thmac;
+
+               /* the subflow req id is valid, fetched via subflow_check_req()
+                * and subflow_token_join_request()
+                */
+               subflow_set_local_id(new_ctx, subflow_req->local_id);
        }
 }
 
@@ -1789,6 +1835,7 @@ void __init mptcp_subflow_init(void)
        subflow_specific.conn_request = subflow_v4_conn_request;
        subflow_specific.syn_recv_sock = subflow_syn_recv_sock;
        subflow_specific.sk_rx_dst_set = subflow_finish_connect;
+       subflow_specific.rebuild_header = subflow_rebuild_header;
 
        tcp_prot_override = tcp_prot;
        tcp_prot_override.release_cb = tcp_release_cb_override;
@@ -1801,6 +1848,7 @@ void __init mptcp_subflow_init(void)
        subflow_v6_specific.conn_request = subflow_v6_conn_request;
        subflow_v6_specific.syn_recv_sock = subflow_syn_recv_sock;
        subflow_v6_specific.sk_rx_dst_set = subflow_finish_connect;
+       subflow_v6_specific.rebuild_header = subflow_v6_rebuild_header;
 
        subflow_v6m_specific = subflow_v6_specific;
        subflow_v6m_specific.queue_xmit = ipv4_specific.queue_xmit;
@@ -1808,6 +1856,7 @@ void __init mptcp_subflow_init(void)
        subflow_v6m_specific.net_header_len = ipv4_specific.net_header_len;
        subflow_v6m_specific.mtu_reduced = ipv4_specific.mtu_reduced;
        subflow_v6m_specific.net_frag_header_len = 0;
+       subflow_v6m_specific.rebuild_header = subflow_rebuild_header;
 
        tcpv6_prot_override = tcpv6_prot;
        tcpv6_prot_override.release_cb = tcp_release_cb_override;