mptcp: implement delegated actions

On MPTCP-level ack reception, the packet scheduler
may select a subflow other then the current one.

Prior to this commit we rely on the workqueue to trigger
action on such subflow.

This changeset introduces an infrastructure that allows
any MPTCP subflow to schedule actions (MPTCP xmit) on
others subflows without resorting to (multiple) process
reschedule.

A dummy NAPI instance is used instead. When MPTCP needs to
trigger action an a different subflow, it enqueues the target
subflow on the NAPI backlog and schedule such instance as needed.

The dummy NAPI poll method walks the sockets backlog and tries
to acquire the (BH) socket lock on each of them. If the socket
is owned by the user space, the action will be completed by
the sock release cb, otherwise push is started.

This change leverages the delegated action infrastructure
to avoid invoking the MPTCP worker to spool the pending data,
when the packet scheduler picks a subflow other then the one
currently processing the incoming MPTCP-level ack.

Additionally we further refine the subflow selection
invoking the packet scheduler for each chunk of data
even inside __mptcp_subflow_push_pending().

v1 -> v2:
 - fix possible UaF at shutdown time, resetting sock ops
   after removing the ulp context

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

1 files changed, 67 insertions, 0 deletions

diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 871534df6140..1460705aaad0 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -378,6 +378,15 @@ enum mptcp_data_avail {
 	MPTCP_SUBFLOW_OOO_DATA
 };
 
+struct mptcp_delegated_action {
+	struct napi_struct napi;
+	struct list_head head;
+};
+
+DECLARE_PER_CPU(struct mptcp_delegated_action, mptcp_delegated_actions);
+
+#define MPTCP_DELEGATE_SEND		0
+
 /* MPTCP subflow context */
 struct mptcp_subflow_context {
 	struct	list_head node;/* conn_list of subflows */
@@ -415,6 +424,9 @@ struct mptcp_subflow_context {
 	u8	local_id;
 	u8	remote_id;
 
+	long	delegated_status;
+	struct	list_head delegated_node;   /* link into delegated_action, protected by local BH */
+
 	struct	sock *tcp_sock;	    /* tcp sk backpointer */
 	struct	sock *conn;	    /* parent mptcp_sock */
 	const	struct inet_connection_sock_af_ops *icsk_af_ops;
@@ -463,6 +475,61 @@ static inline void mptcp_add_pending_subflow(struct mptcp_sock *msk,
 	spin_unlock_bh(&msk->join_list_lock);
 }
 
+void mptcp_subflow_process_delegated(struct sock *ssk);
+
+static inline void mptcp_subflow_delegate(struct mptcp_subflow_context *subflow)
+{
+	struct mptcp_delegated_action *delegated;
+	bool schedule;
+
+	/* The implied barrier pairs with mptcp_subflow_delegated_done(), and
+	 * ensures the below list check sees list updates done prior to status
+	 * bit changes
+	 */
+	if (!test_and_set_bit(MPTCP_DELEGATE_SEND, &subflow->delegated_status)) {
+		/* still on delegated list from previous scheduling */
+		if (!list_empty(&subflow->delegated_node))
+			return;
+
+		/* the caller held the subflow bh socket lock */
+		lockdep_assert_in_softirq();
+
+		delegated = this_cpu_ptr(&mptcp_delegated_actions);
+		schedule = list_empty(&delegated->head);
+		list_add_tail(&subflow->delegated_node, &delegated->head);
+		sock_hold(mptcp_subflow_tcp_sock(subflow));
+		if (schedule)
+			napi_schedule(&delegated->napi);
+	}
+}
+
+static inline struct mptcp_subflow_context *
+mptcp_subflow_delegated_next(struct mptcp_delegated_action *delegated)
+{
+	struct mptcp_subflow_context *ret;
+
+	if (list_empty(&delegated->head))
+		return NULL;
+
+	ret = list_first_entry(&delegated->head, struct mptcp_subflow_context, delegated_node);
+	list_del_init(&ret->delegated_node);
+	return ret;
+}
+
+static inline bool mptcp_subflow_has_delegated_action(const struct mptcp_subflow_context *subflow)
+{
+	return test_bit(MPTCP_DELEGATE_SEND, &subflow->delegated_status);
+}
+
+static inline void mptcp_subflow_delegated_done(struct mptcp_subflow_context *subflow)
+{
+	/* pairs with mptcp_subflow_delegate, ensures delegate_node is updated before
+	 * touching the status bit
+	 */
+	smp_wmb();
+	clear_bit(MPTCP_DELEGATE_SEND, &subflow->delegated_status);
+}
+
 int mptcp_is_enabled(struct net *net);
 unsigned int mptcp_get_add_addr_timeout(struct net *net);
 void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow,