mptcp: refactor token container

Replace the radix tree with a hash table allocated
at boot time. The radix tree has some shortcoming:
a single lock is contented by all the mptcp operation,
the lookup currently use such lock, and traversing
all the items would require a lock, too.

With hash table instead we trade a little memory to
address all the above - a per bucket lock is used.

To hash the MPTCP sockets, we re-use the msk' sk_node
entry: the MPTCP sockets are never hashed by the stack.
Replace the existing hash proto callbacks with a dummy
implementation, annotating the above constraint.

Additionally refactor the token creation to code to:

- limit the number of consecutive attempts to a fixed
maximum. Hitting a hash bucket with a long chain is
considered a failed attempt

- accept() no longer can fail to token management.

- if token creation fails at connect() time, we do
fallback to TCP (before the connection was closed)

v1 -> v2:
 - fix "no newline at end of file" - Jakub

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

1 files changed, 7 insertions, 12 deletions

diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index c2389ba2d4ee..102db8c88e97 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -32,12 +32,9 @@ static void SUBFLOW_REQ_INC_STATS(struct request_sock *req,
 static int subflow_rebuild_header(struct sock *sk)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
-	int local_id, err = 0;
+	int local_id;
 
-	if (subflow->request_mptcp && !subflow->token) {
-		pr_debug("subflow=%p", sk);
-		err = mptcp_token_new_connect(sk);
-	} else if (subflow->request_join && !subflow->local_nonce) {
+	if (subflow->request_join && !subflow->local_nonce) {
 		struct mptcp_sock *msk = (struct mptcp_sock *)subflow->conn;
 
 		pr_debug("subflow=%p", sk);
@@ -57,9 +54,6 @@ static int subflow_rebuild_header(struct sock *sk)
 	}
 
 out:
-	if (err)
-		return err;
-
 	return subflow->icsk_af_ops->rebuild_header(sk);
 }
 
@@ -72,8 +66,7 @@ static void subflow_req_destructor(struct request_sock *req)
 	if (subflow_req->msk)
 		sock_put((struct sock *)subflow_req->msk);
 
-	if (subflow_req->mp_capable)
-		mptcp_token_destroy_request(subflow_req->token);
+	mptcp_token_destroy_request(req);
 	tcp_request_sock_ops.destructor(req);
 }
 
@@ -135,6 +128,7 @@ static void subflow_init_req(struct request_sock *req,
 	subflow_req->mp_capable = 0;
 	subflow_req->mp_join = 0;
 	subflow_req->msk = NULL;
+	mptcp_token_init_request(req);
 
 #ifdef CONFIG_TCP_MD5SIG
 	/* no MPTCP if MD5SIG is enabled on this socket or we may run out of
@@ -250,7 +244,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 		subflow->remote_nonce = mp_opt.nonce;
 		pr_debug("subflow=%p, thmac=%llu, remote_nonce=%u", subflow,
 			 subflow->thmac, subflow->remote_nonce);
-	} else if (subflow->request_mptcp) {
+	} else {
 		tp->is_mptcp = 0;
 	}
 
@@ -386,7 +380,7 @@ static void mptcp_sock_destruct(struct sock *sk)
 		sock_orphan(sk);
 	}
 
-	mptcp_token_destroy(mptcp_sk(sk)->token);
+	mptcp_token_destroy(mptcp_sk(sk));
 	inet_sock_destruct(sk);
 }
 
@@ -505,6 +499,7 @@ create_child:
 			 */
 			new_msk->sk_destruct = mptcp_sock_destruct;
 			mptcp_pm_new_connection(mptcp_sk(new_msk), 1);
+			mptcp_token_accept(subflow_req, mptcp_sk(new_msk));
 			ctx->conn = new_msk;
 			new_msk = NULL;