mptcp: add new sock flag to deal with join subflows

MP_JOIN subflows must not land into the accept queue.
Currently tcp_check_req() calls an mptcp specific helper
to detect such scenario.

Such helper leverages the subflow context to check for
MP_JOIN subflows. We need to deal also with MP JOIN
failures, even when the subflow context is not available
due allocation failure.

A possible solution would be changing the syn_recv_sock()
signature to allow returning a more descriptive action/
error code and deal with that in tcp_check_req().

Since the above need is MPTCP specific, this patch instead
uses a TCP request socket hole to add a MPTCP specific flag.
Such flag is used by the MPTCP syn_recv_sock() to tell
tcp_check_req() how to deal with the request socket.

This change is a no-op for !MPTCP build, and makes the
MPTCP code simpler. It allows also the next patch to deal
correctly with MP JOIN failure.

v1 -> v2:
 - be more conservative on drop_req initialization (Mat)

RFC -> v1:
 - move the drop_req bit inside tcp_request_sock (Eric)

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Reviewed-by: Christoph Paasch <cpaasch@apple.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index e60db06..bf44e85 100644 (file)
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -120,6 +120,9 @@ struct tcp_request_sock {
        u64                             snt_synack; /* first SYNACK sent time */
        bool                            tfo_listener;
        bool                            is_mptcp;
+#if IS_ENABLED(CONFIG_MPTCP)
+       bool                            drop_req;
+#endif
        u32                             txhash;
        u32                             rcv_isn;
        u32                             snt_isn;

diff --git a/include/net/mptcp.h b/include/net/mptcp.h
index e602756..c4a6ef4 100644 (file)
--- a/include/net/mptcp.h
+++ b/include/net/mptcp.h
@@ -68,6 +68,11 @@ static inline bool rsk_is_mptcp(const struct request_sock *req)
        return tcp_rsk(req)->is_mptcp;
 }
 
+static inline bool rsk_drop_req(const struct request_sock *req)
+{
+       return tcp_rsk(req)->is_mptcp && tcp_rsk(req)->drop_req;
+}
+
 void mptcp_space(const struct sock *ssk, int *space, int *full_space);
 bool mptcp_syn_options(struct sock *sk, const struct sk_buff *skb,
                       unsigned int *size, struct mptcp_out_options *opts);
@@ -121,8 +126,6 @@ static inline bool mptcp_skb_can_collapse(const struct sk_buff *to,
                                 skb_ext_find(from, SKB_EXT_MPTCP));
 }
 
-bool mptcp_sk_is_subflow(const struct sock *sk);
-
 void mptcp_seq_show(struct seq_file *seq);
 #else
 
@@ -140,6 +143,11 @@ static inline bool rsk_is_mptcp(const struct request_sock *req)
        return false;
 }
 
+static inline bool rsk_drop_req(const struct request_sock *req)
+{
+       return false;
+}
+
 static inline void mptcp_parse_option(const struct sk_buff *skb,
                                      const unsigned char *ptr, int opsize,
                                      struct tcp_options_received *opt_rx)
@@ -190,11 +198,6 @@ static inline bool mptcp_skb_can_collapse(const struct sk_buff *to,
        return true;
 }
 
-static inline bool mptcp_sk_is_subflow(const struct sock *sk)
-{
-       return false;
-}
-
 static inline void mptcp_space(const struct sock *ssk, int *s, int *fs) { }
 static inline void mptcp_seq_show(struct seq_file *seq) { }
 #endif /* CONFIG_MPTCP */

diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 7e40322..495dda2 100644 (file)
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -774,7 +774,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
        if (!child)
                goto listen_overflow;
 
-       if (own_req && sk_is_mptcp(child) && mptcp_sk_is_subflow(child)) {
+       if (own_req && rsk_drop_req(req)) {
                reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req);
                inet_csk_reqsk_queue_drop_and_put(sk, req);
                return child;

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index e1f2301..a61e60e 100644 (file)
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1638,13 +1638,6 @@ bool mptcp_finish_join(struct sock *sk)
        return ret;
 }
 
-bool mptcp_sk_is_subflow(const struct sock *sk)
-{
-       struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
-
-       return subflow->mp_join == 1;
-}
-
 static bool mptcp_memory_free(const struct sock *sk, int wake)
 {
        struct mptcp_sock *msk = mptcp_sk(sk);

diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 009d5c4..5e03ed8 100644 (file)
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -470,6 +470,8 @@ create_child:
        if (child && *own_req) {
                struct mptcp_subflow_context *ctx = mptcp_subflow_ctx(child);
 
+               tcp_rsk(req)->drop_req = false;
+
                /* we need to fallback on ctx allocation failure and on pre-reqs
                 * checking above. In the latter scenario we additionally need
                 * to reset the context to non MPTCP status.
@@ -512,6 +514,7 @@ create_child:
                                goto close_child;
 
                        SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKRX);
+                       tcp_rsk(req)->drop_req = true;
                }
        }