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, 45 insertions, 0 deletions

diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 1ca0c82b0dbd..721059916c96 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -18,12 +18,15 @@
 #include <net/tcp.h>
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
 #include <net/ip6_route.h>
+#include <net/transp_v6.h>
 #endif
 #include <net/mptcp.h>
 #include <uapi/linux/mptcp.h>
 #include "protocol.h"
 #include "mib.h"
 
+static void mptcp_subflow_ops_undo_override(struct sock *ssk);
+
 static void SUBFLOW_REQ_INC_STATS(struct request_sock *req,
 				  enum linux_mptcp_mib_field field)
 {
@@ -428,6 +431,7 @@ drop:
 static struct tcp_request_sock_ops subflow_request_sock_ipv6_ops;
 static struct inet_connection_sock_af_ops subflow_v6_specific;
 static struct inet_connection_sock_af_ops subflow_v6m_specific;
+static struct proto tcpv6_prot_override;
 
 static int subflow_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 {
@@ -509,6 +513,8 @@ static void subflow_ulp_fallback(struct sock *sk,
 	icsk->icsk_ulp_ops = NULL;
 	rcu_assign_pointer(icsk->icsk_ulp_data, NULL);
 	tcp_sk(sk)->is_mptcp = 0;
+
+	mptcp_subflow_ops_undo_override(sk);
 }
 
 static void subflow_drop_ctx(struct sock *ssk)
@@ -682,6 +688,7 @@ dispose_child:
 }
 
 static struct inet_connection_sock_af_ops subflow_specific;
+static struct proto tcp_prot_override;
 
 enum mapping_status {
 	MAPPING_OK,
@@ -1203,6 +1210,25 @@ static void mptcp_attach_cgroup(struct sock *parent, struct sock *child)
 #endif /* CONFIG_SOCK_CGROUP_DATA */
 }
 
+static void mptcp_subflow_ops_override(struct sock *ssk)
+{
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+	if (ssk->sk_prot == &tcpv6_prot)
+		ssk->sk_prot = &tcpv6_prot_override;
+	else
+#endif
+		ssk->sk_prot = &tcp_prot_override;
+}
+
+static void mptcp_subflow_ops_undo_override(struct sock *ssk)
+{
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+	if (ssk->sk_prot == &tcpv6_prot_override)
+		ssk->sk_prot = &tcpv6_prot;
+	else
+#endif
+		ssk->sk_prot = &tcp_prot;
+}
 int mptcp_subflow_create_socket(struct sock *sk, struct socket **new_sock)
 {
 	struct mptcp_subflow_context *subflow;
@@ -1258,6 +1284,7 @@ int mptcp_subflow_create_socket(struct sock *sk, struct socket **new_sock)
 	*new_sock = sf;
 	sock_hold(sk);
 	subflow->conn = sk;
+	mptcp_subflow_ops_override(sf->sk);
 
 	return 0;
 }
@@ -1274,6 +1301,7 @@ static struct mptcp_subflow_context *subflow_create_ctx(struct sock *sk,
 
 	rcu_assign_pointer(icsk->icsk_ulp_data, ctx);
 	INIT_LIST_HEAD(&ctx->node);
+	INIT_LIST_HEAD(&ctx->delegated_node);
 
 	pr_debug("subflow=%p", ctx);
 
@@ -1386,6 +1414,7 @@ static void subflow_ulp_release(struct sock *ssk)
 		sock_put(sk);
 	}
 
+	mptcp_subflow_ops_undo_override(ssk);
 	if (release)
 		kfree_rcu(ctx, rcu);
 }
@@ -1439,6 +1468,16 @@ static void subflow_ulp_clone(const struct request_sock *req,
 	}
 }
 
+static void tcp_release_cb_override(struct sock *ssk)
+{
+	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
+
+	if (mptcp_subflow_has_delegated_action(subflow))
+		mptcp_subflow_process_delegated(ssk);
+
+	tcp_release_cb(ssk);
+}
+
 static struct tcp_ulp_ops subflow_ulp_ops __read_mostly = {
 	.name		= "mptcp",
 	.owner		= THIS_MODULE,
@@ -1479,6 +1518,9 @@ void __init mptcp_subflow_init(void)
 	subflow_specific.syn_recv_sock = subflow_syn_recv_sock;
 	subflow_specific.sk_rx_dst_set = subflow_finish_connect;
 
+	tcp_prot_override = tcp_prot;
+	tcp_prot_override.release_cb = tcp_release_cb_override;
+
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
 	subflow_request_sock_ipv6_ops = tcp_request_sock_ipv6_ops;
 	subflow_request_sock_ipv6_ops.route_req = subflow_v6_route_req;
@@ -1494,6 +1536,9 @@ 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;
+
+	tcpv6_prot_override = tcpv6_prot;
+	tcpv6_prot_override.release_cb = tcp_release_cb_override;
 #endif
 
 	mptcp_diag_subflow_init(&subflow_ulp_ops);