Merge branch 'mptcp-genl-events'

Mat Martineau says:

====================
mptcp: Add genl events for connection info

This series from the MPTCP tree adds genl multicast events that are
important for implementing a userspace path manager. In MPTCP, a path
manager is responsible for adding or removing additional subflows on
each MPTCP connection. The in-kernel path manager (already part of the
kernel) is a better fit for many server use cases, but the additional
flexibility of userspace path managers is often useful for client
devices.

Patches 1, 2, 4, 5, and 6 do some refactoring to streamline the netlink
event implementation in the final patch.

Patch 3 improves the timeliness of subflow destruction to ensure the
'subflow closed' event will be sent soon enough.

Patch 7 allows use of the GENL_UNS_ADMIN_PERM flag on genl mcast groups
to mandate CAP_NET_ADMIN, which is important to protect token information
in the MPTCP events. This is a genetlink change.

Patch 8 adds the MPTCP netlink events.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/genetlink.h

@@ -14,6 +14,7 @@
  */
 struct genl_multicast_group {
 	char			name[GENL_NAMSIZ];
+	u8			flags;
 };
 
 struct genl_ops;

include/uapi/linux/mptcp.h

@@ -36,6 +36,7 @@ enum {
 /* netlink interface */
 #define MPTCP_PM_NAME		"mptcp_pm"
 #define MPTCP_PM_CMD_GRP_NAME	"mptcp_pm_cmds"
+#define MPTCP_PM_EV_GRP_NAME	"mptcp_pm_events"
 #define MPTCP_PM_VER		0x1
 
 /*
@@ -104,4 +105,77 @@ struct mptcp_info {
 	__u64	mptcpi_rcv_nxt;
 };
 
+/*
+ * MPTCP_EVENT_CREATED: token, family, saddr4 | saddr6, daddr4 | daddr6,
+ *                      sport, dport
+ * A new MPTCP connection has been created. It is the good time to allocate
+ * memory and send ADD_ADDR if needed. Depending on the traffic-patterns
+ * it can take a long time until the MPTCP_EVENT_ESTABLISHED is sent.
+ *
+ * MPTCP_EVENT_ESTABLISHED: token, family, saddr4 | saddr6, daddr4 | daddr6,
+ *			    sport, dport
+ * A MPTCP connection is established (can start new subflows).
+ *
+ * MPTCP_EVENT_CLOSED: token
+ * A MPTCP connection has stopped.
+ *
+ * MPTCP_EVENT_ANNOUNCED: token, rem_id, family, daddr4 | daddr6 [, dport]
+ * A new address has been announced by the peer.
+ *
+ * MPTCP_EVENT_REMOVED: token, rem_id
+ * An address has been lost by the peer.
+ *
+ * MPTCP_EVENT_SUB_ESTABLISHED: token, family, saddr4 | saddr6,
+ *                              daddr4 | daddr6, sport, dport, backup,
+ *                              if_idx [, error]
+ * A new subflow has been established. 'error' should not be set.
+ *
+ * MPTCP_EVENT_SUB_CLOSED: token, family, saddr4 | saddr6, daddr4 | daddr6,
+ *                         sport, dport, backup, if_idx [, error]
+ * A subflow has been closed. An error (copy of sk_err) could be set if an
+ * error has been detected for this subflow.
+ *
+ * MPTCP_EVENT_SUB_PRIORITY: token, family, saddr4 | saddr6, daddr4 | daddr6,
+ *                           sport, dport, backup, if_idx [, error]
+ *       The priority of a subflow has changed. 'error' should not be set.
+ */
+enum mptcp_event_type {
+	MPTCP_EVENT_UNSPEC = 0,
+	MPTCP_EVENT_CREATED = 1,
+	MPTCP_EVENT_ESTABLISHED = 2,
+	MPTCP_EVENT_CLOSED = 3,
+
+	MPTCP_EVENT_ANNOUNCED = 6,
+	MPTCP_EVENT_REMOVED = 7,
+
+	MPTCP_EVENT_SUB_ESTABLISHED = 10,
+	MPTCP_EVENT_SUB_CLOSED = 11,
+
+	MPTCP_EVENT_SUB_PRIORITY = 13,
+};
+
+enum mptcp_event_attr {
+	MPTCP_ATTR_UNSPEC = 0,
+
+	MPTCP_ATTR_TOKEN,	/* u32 */
+	MPTCP_ATTR_FAMILY,	/* u16 */
+	MPTCP_ATTR_LOC_ID,	/* u8 */
+	MPTCP_ATTR_REM_ID,	/* u8 */
+	MPTCP_ATTR_SADDR4,	/* be32 */
+	MPTCP_ATTR_SADDR6,	/* struct in6_addr */
+	MPTCP_ATTR_DADDR4,	/* be32 */
+	MPTCP_ATTR_DADDR6,	/* struct in6_addr */
+	MPTCP_ATTR_SPORT,	/* be16 */
+	MPTCP_ATTR_DPORT,	/* be16 */
+	MPTCP_ATTR_BACKUP,	/* u8 */
+	MPTCP_ATTR_ERROR,	/* u8 */
+	MPTCP_ATTR_FLAGS,	/* u16 */
+	MPTCP_ATTR_TIMEOUT,	/* u32 */
+	MPTCP_ATTR_IF_IDX,	/* s32 */
+
+	__MPTCP_ATTR_AFTER_LAST
+};
+
+#define MPTCP_ATTR_MAX (__MPTCP_ATTR_AFTER_LAST - 1)
+
 #endif /* _UAPI_MPTCP_H */

net/mptcp/options.c

@@ -867,7 +867,7 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk,
 		clear_3rdack_retransmission(ssk);
 		mptcp_pm_subflow_established(msk, subflow);
 	} else {
-		mptcp_pm_fully_established(msk);
+		mptcp_pm_fully_established(msk, ssk, GFP_ATOMIC);
 	}
 	return true;
 

net/mptcp/pm.c

@@ -68,13 +68,14 @@ int mptcp_pm_remove_subflow(struct mptcp_sock *msk, u8 local_id)
 
 /* path manager event handlers */
 
-void mptcp_pm_new_connection(struct mptcp_sock *msk, int server_side)
+void mptcp_pm_new_connection(struct mptcp_sock *msk, const struct sock *ssk, int server_side)
 {
 	struct mptcp_pm_data *pm = &msk->pm;
 
 	pr_debug("msk=%p, token=%u side=%d", msk, msk->token, server_side);
 
 	WRITE_ONCE(pm->server_side, server_side);
+	mptcp_event(MPTCP_EVENT_CREATED, msk, ssk, GFP_ATOMIC);
 }
 
 bool mptcp_pm_allow_new_subflow(struct mptcp_sock *msk)
@@ -119,16 +120,13 @@ static bool mptcp_pm_schedule_work(struct mptcp_sock *msk,
 	return true;
 }
 
-void mptcp_pm_fully_established(struct mptcp_sock *msk)
+void mptcp_pm_fully_established(struct mptcp_sock *msk, const struct sock *ssk, gfp_t gfp)
 {
 	struct mptcp_pm_data *pm = &msk->pm;
+	bool announce = false;
 
 	pr_debug("msk=%p", msk);
 
-	/* try to avoid acquiring the lock below */
-	if (!READ_ONCE(pm->work_pending))
-		return;
-
 	spin_lock_bh(&pm->lock);
 
 	/* mptcp_pm_fully_established() can be invoked by multiple
@@ -138,9 +136,15 @@ void mptcp_pm_fully_established(struct mptcp_sock *msk)
 	if (READ_ONCE(pm->work_pending) &&
 	    !(msk->pm.status & BIT(MPTCP_PM_ALREADY_ESTABLISHED)))
 		mptcp_pm_schedule_work(msk, MPTCP_PM_ESTABLISHED);
-	msk->pm.status |= BIT(MPTCP_PM_ALREADY_ESTABLISHED);
 
+	if ((msk->pm.status & BIT(MPTCP_PM_ALREADY_ESTABLISHED)) == 0)
+		announce = true;
+
+	msk->pm.status |= BIT(MPTCP_PM_ALREADY_ESTABLISHED);
 	spin_unlock_bh(&pm->lock);
+
+	if (announce)
+		mptcp_event(MPTCP_EVENT_ESTABLISHED, msk, ssk, gfp);
 }
 
 void mptcp_pm_connection_closed(struct mptcp_sock *msk)
@@ -179,6 +183,8 @@ void mptcp_pm_add_addr_received(struct mptcp_sock *msk,
 	pr_debug("msk=%p remote_id=%d accept=%d", msk, addr->id,
 		 READ_ONCE(pm->accept_addr));
 
+	mptcp_event_addr_announced(msk, addr);
+
 	spin_lock_bh(&pm->lock);
 
 	if (!READ_ONCE(pm->accept_addr)) {
@@ -205,6 +211,8 @@ void mptcp_pm_rm_addr_received(struct mptcp_sock *msk, u8 rm_id)
 
 	pr_debug("msk=%p remote_id=%d", msk, rm_id);
 
+	mptcp_event_addr_removed(msk, rm_id);
+
 	spin_lock_bh(&pm->lock);
 	mptcp_pm_schedule_work(msk, MPTCP_PM_RM_ADDR_RECEIVED);
 	pm->rm_id = rm_id;
@@ -217,6 +225,8 @@ void mptcp_pm_mp_prio_received(struct sock *sk, u8 bkup)
 
 	pr_debug("subflow->backup=%d, bkup=%d\n", subflow->backup, bkup);
 	subflow->backup = bkup;
+
+	mptcp_event(MPTCP_EVENT_SUB_PRIORITY, mptcp_sk(subflow->conn), sk, GFP_ATOMIC);
 }
 
 /* path manager helpers */

net/mptcp/protocol.c

@@ -2114,7 +2114,7 @@ static struct sock *mptcp_subflow_get_retrans(const struct mptcp_sock *msk)
  * so we need to use tcp_close() after detaching them from the mptcp
  * parent socket.
  */
-void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
+static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
 			      struct mptcp_subflow_context *subflow)
 {
 	list_del(&subflow->node);
@@ -2147,40 +2147,17 @@ void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
 	sock_put(ssk);
 }
 
-static unsigned int mptcp_sync_mss(struct sock *sk, u32 pmtu)
+void mptcp_close_ssk(struct sock *sk, struct sock *ssk,
+		     struct mptcp_subflow_context *subflow)
 {
-	return 0;
+	if (sk->sk_state == TCP_ESTABLISHED)
+		mptcp_event(MPTCP_EVENT_SUB_CLOSED, mptcp_sk(sk), ssk, GFP_KERNEL);
+	__mptcp_close_ssk(sk, ssk, subflow);
 }
 
-static void pm_work(struct mptcp_sock *msk)
+static unsigned int mptcp_sync_mss(struct sock *sk, u32 pmtu)
 {
-	struct mptcp_pm_data *pm = &msk->pm;
-
-	spin_lock_bh(&msk->pm.lock);
-
-	pr_debug("msk=%p status=%x", msk, pm->status);
-	if (pm->status & BIT(MPTCP_PM_ADD_ADDR_RECEIVED)) {
-		pm->status &= ~BIT(MPTCP_PM_ADD_ADDR_RECEIVED);
-		mptcp_pm_nl_add_addr_received(msk);
-	}
-	if (pm->status & BIT(MPTCP_PM_ADD_ADDR_SEND_ACK)) {
-		pm->status &= ~BIT(MPTCP_PM_ADD_ADDR_SEND_ACK);
-		mptcp_pm_nl_add_addr_send_ack(msk);
-	}
-	if (pm->status & BIT(MPTCP_PM_RM_ADDR_RECEIVED)) {
-		pm->status &= ~BIT(MPTCP_PM_RM_ADDR_RECEIVED);
-		mptcp_pm_nl_rm_addr_received(msk);
-	}
-	if (pm->status & BIT(MPTCP_PM_ESTABLISHED)) {
-		pm->status &= ~BIT(MPTCP_PM_ESTABLISHED);
-		mptcp_pm_nl_fully_established(msk);
-	}
-	if (pm->status & BIT(MPTCP_PM_SUBFLOW_ESTABLISHED)) {
-		pm->status &= ~BIT(MPTCP_PM_SUBFLOW_ESTABLISHED);
-		mptcp_pm_nl_subflow_established(msk);
-	}
-
-	spin_unlock_bh(&msk->pm.lock);
+	return 0;
 }
 
 static void __mptcp_close_subflow(struct mptcp_sock *msk)
@@ -2195,7 +2172,11 @@ static void __mptcp_close_subflow(struct mptcp_sock *msk)
 		if (inet_sk_state_load(ssk) != TCP_CLOSE)
 			continue;
 
-		__mptcp_close_ssk((struct sock *)msk, ssk, subflow);
+		/* 'subflow_data_ready' will re-sched once rx queue is empty */
+		if (!skb_queue_empty_lockless(&ssk->sk_receive_queue))
+			continue;
+
+		mptcp_close_ssk((struct sock *)msk, ssk, subflow);
 	}
 }
 
@@ -2267,11 +2248,8 @@ static void mptcp_worker(struct work_struct *work)
 
 	mptcp_check_fastclose(msk);
 
-	if (test_and_clear_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags))
-		__mptcp_close_subflow(msk);
-
 	if (msk->pm.status)
-		pm_work(msk);
+		mptcp_pm_nl_work(msk);
 
 	if (test_and_clear_bit(MPTCP_WORK_EOF, &msk->flags))
 		mptcp_check_for_eof(msk);
@@ -2291,6 +2269,9 @@ static void mptcp_worker(struct work_struct *work)
 		goto unlock;
 	}
 
+	if (test_and_clear_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags))
+		__mptcp_close_subflow(msk);
+
 	if (!test_and_clear_bit(MPTCP_WORK_RTX, &msk->flags))
 		goto unlock;
 
@@ -2607,6 +2588,10 @@ static void mptcp_close(struct sock *sk, long timeout)
 	release_sock(sk);
 	if (do_cancel_work)
 		mptcp_cancel_work(sk);
+
+	if (mptcp_sk(sk)->token)
+		mptcp_event(MPTCP_EVENT_CLOSED, mptcp_sk(sk), NULL, GFP_KERNEL);
+
 	sock_put(sk);
 }
 
@@ -3049,7 +3034,7 @@ void mptcp_finish_connect(struct sock *ssk)
 	WRITE_ONCE(msk->can_ack, 1);
 	WRITE_ONCE(msk->snd_una, msk->write_seq);
 
-	mptcp_pm_new_connection(msk, 0);
+	mptcp_pm_new_connection(msk, ssk, 0);
 
 	mptcp_rcv_space_init(msk, ssk);
 }
@@ -3078,7 +3063,7 @@ bool mptcp_finish_join(struct sock *ssk)
 		return false;
 
 	if (!msk->pm.server_side)
-		return true;
+		goto out;
 
 	if (!mptcp_pm_allow_new_subflow(msk))
 		return false;
@@ -3105,6 +3090,8 @@ bool mptcp_finish_join(struct sock *ssk)
 	if (parent_sock && !ssk->sk_socket)
 		mptcp_sock_graft(ssk, parent_sock);
 	subflow->map_seq = READ_ONCE(msk->ack_seq);
+out:
+	mptcp_event(MPTCP_EVENT_SUB_ESTABLISHED, msk, ssk, GFP_ATOMIC);
 	return true;
 }
 
@@ -3281,9 +3268,8 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
 		struct mptcp_sock *msk = mptcp_sk(newsock->sk);
 		struct mptcp_subflow_context *subflow;
 		struct sock *newsk = newsock->sk;
-		bool slowpath;
 
-		slowpath = lock_sock_fast(newsk);
+		lock_sock(newsk);
 
 		/* PM/worker can now acquire the first subflow socket
 		 * lock without racing with listener queue cleanup,
@@ -3293,7 +3279,7 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
 		list_add(&subflow->node, &msk->conn_list);
 		sock_hold(msk->first);
 		if (mptcp_is_fully_established(newsk))
-			mptcp_pm_fully_established(msk);
+			mptcp_pm_fully_established(msk, msk->first, GFP_KERNEL);
 
 		mptcp_copy_inaddrs(newsk, msk->first);
 		mptcp_rcv_space_init(msk, msk->first);
@@ -3309,7 +3295,7 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
 			if (!ssk->sk_socket)
 				mptcp_sock_graft(ssk, newsock);
 		}
-		unlock_sock_fast(newsk, slowpath);
+		release_sock(newsk);
 	}
 
 	if (inet_csk_listen_poll(ssock->sk))

net/mptcp/protocol.h

@@ -10,6 +10,7 @@
 #include <linux/random.h>
 #include <net/tcp.h>
 #include <net/inet_connection_sock.h>
+#include <uapi/linux/mptcp.h>
 
 #define MPTCP_SUPPORTED_VERSION	1
 
@@ -539,7 +540,7 @@ void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow,
 bool mptcp_subflow_data_available(struct sock *sk);
 void __init mptcp_subflow_init(void);
 void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how);
-void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
+void mptcp_close_ssk(struct sock *sk, struct sock *ssk,
 		     struct mptcp_subflow_context *subflow);
 void mptcp_subflow_reset(struct sock *ssk);
 void mptcp_sock_graft(struct sock *sk, struct socket *parent);
@@ -639,8 +640,8 @@ void mptcp_crypto_hmac_sha(u64 key1, u64 key2, u8 *msg, int len, void *hmac);
 
 void __init mptcp_pm_init(void);
 void mptcp_pm_data_init(struct mptcp_sock *msk);
-void mptcp_pm_new_connection(struct mptcp_sock *msk, int server_side);
-void mptcp_pm_fully_established(struct mptcp_sock *msk);
+void mptcp_pm_new_connection(struct mptcp_sock *msk, const struct sock *ssk, int server_side);
+void mptcp_pm_fully_established(struct mptcp_sock *msk, const struct sock *ssk, gfp_t gfp);
 bool mptcp_pm_allow_new_subflow(struct mptcp_sock *msk);
 void mptcp_pm_connection_closed(struct mptcp_sock *msk);
 void mptcp_pm_subflow_established(struct mptcp_sock *msk,
@@ -666,6 +667,11 @@ int mptcp_pm_announce_addr(struct mptcp_sock *msk,
 int mptcp_pm_remove_addr(struct mptcp_sock *msk, u8 local_id);
 int mptcp_pm_remove_subflow(struct mptcp_sock *msk, u8 local_id);
 
+void mptcp_event(enum mptcp_event_type type, const struct mptcp_sock *msk,
+		 const struct sock *ssk, gfp_t gfp);
+void mptcp_event_addr_announced(const struct mptcp_sock *msk, const struct mptcp_addr_info *info);
+void mptcp_event_addr_removed(const struct mptcp_sock *msk, u8 id);
+
 static inline bool mptcp_pm_should_add_signal(struct mptcp_sock *msk)
 {
 	return READ_ONCE(msk->pm.addr_signal) & BIT(MPTCP_ADD_ADDR_SIGNAL);
@@ -713,11 +719,7 @@ int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc);
 
 void __init mptcp_pm_nl_init(void);
 void mptcp_pm_nl_data_init(struct mptcp_sock *msk);
-void mptcp_pm_nl_fully_established(struct mptcp_sock *msk);
-void mptcp_pm_nl_subflow_established(struct mptcp_sock *msk);
-void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk);
-void mptcp_pm_nl_add_addr_send_ack(struct mptcp_sock *msk);
-void mptcp_pm_nl_rm_addr_received(struct mptcp_sock *msk);
+void mptcp_pm_nl_work(struct mptcp_sock *msk);
 void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk, u8 rm_id);
 int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc);
 unsigned int mptcp_pm_get_add_addr_signal_max(struct mptcp_sock *msk);

net/mptcp/subflow.c

@@ -675,7 +675,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
 			 * created mptcp socket
 			 */
 			new_msk->sk_destruct = mptcp_sock_destruct;
-			mptcp_pm_new_connection(mptcp_sk(new_msk), 1);
+			mptcp_pm_new_connection(mptcp_sk(new_msk), child, 1);
 			mptcp_token_accept(subflow_req, mptcp_sk(new_msk));
 			ctx->conn = new_msk;
 			new_msk = NULL;
@@ -953,6 +953,22 @@ static void mptcp_subflow_discard_data(struct sock *ssk, struct sk_buff *skb,
 		subflow->map_valid = 0;
 }
 
+/* sched mptcp worker to remove the subflow if no more data is pending */
+static void subflow_sched_work_if_closed(struct mptcp_sock *msk, struct sock *ssk)
+{
+	struct sock *sk = (struct sock *)msk;
+
+	if (likely(ssk->sk_state != TCP_CLOSE))
+		return;
+
+	if (skb_queue_empty(&ssk->sk_receive_queue) &&
+	    !test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags)) {
+		sock_hold(sk);
+		if (!schedule_work(&msk->work))
+			sock_put(sk);
+	}
+}
+
 static bool subflow_check_data_avail(struct sock *ssk)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
@@ -991,11 +1007,11 @@ static bool subflow_check_data_avail(struct sock *ssk)
 		}
 
 		if (status != MAPPING_OK)
-			return false;
+			goto no_data;
 
 		skb = skb_peek(&ssk->sk_receive_queue);
 		if (WARN_ON_ONCE(!skb))
-			return false;
+			goto no_data;
 
 		/* if msk lacks the remote key, this subflow must provide an
 		 * MP_CAPABLE-based mapping
@@ -1029,6 +1045,9 @@ static bool subflow_check_data_avail(struct sock *ssk)
 	}
 	return true;
 
+no_data:
+	subflow_sched_work_if_closed(msk, ssk);
+	return false;
 fatal:
 	/* fatal protocol error, close the socket */
 	/* This barrier is coupled with smp_rmb() in tcp_poll() */
@@ -1413,6 +1432,8 @@ static void subflow_state_change(struct sock *sk)
 	if (mptcp_subflow_data_available(sk))
 		mptcp_data_ready(parent, sk);
 
+	subflow_sched_work_if_closed(mptcp_sk(parent), sk);
+
 	if (__mptcp_check_fallback(mptcp_sk(parent)) &&
 	    !subflow->rx_eof && subflow_is_done(sk)) {
 		subflow->rx_eof = 1;

net/netlink/genetlink.c

@@ -1360,11 +1360,43 @@ static struct genl_family genl_ctrl __ro_after_init = {
 	.netnsok = true,
 };
 
+static int genl_bind(struct net *net, int group)
+{
+	const struct genl_family *family;
+	unsigned int id;
+	int ret = 0;
+
+	genl_lock_all();
+
+	idr_for_each_entry(&genl_fam_idr, family, id) {
+		const struct genl_multicast_group *grp;
+		int i;
+
+		if (family->n_mcgrps == 0)
+			continue;
+
+		i = group - family->mcgrp_offset;
+		if (i < 0 || i >= family->n_mcgrps)
+			continue;
+
+		grp = &family->mcgrps[i];
+		if ((grp->flags & GENL_UNS_ADMIN_PERM) &&
+		    !ns_capable(net->user_ns, CAP_NET_ADMIN))
+			ret = -EPERM;
+
+		break;
+	}
+
+	genl_unlock_all();
+	return ret;
+}
+
 static int __net_init genl_pernet_init(struct net *net)
 {
 	struct netlink_kernel_cfg cfg = {
 		.input		= genl_rcv,
 		.flags		= NL_CFG_F_NONROOT_RECV,
+		.bind		= genl_bind,
 	};
 
 	/* we'll bump the group number right afterwards */