mptcp: add netlink event support

Allow userspace (mptcpd) to subscribe to mptcp genl multicast events.
This implementation reuses the same event API as the mptcp kernel fork
to ease integration of existing tools, e.g. mptcpd.

Supported events include:
1. start and close of an mptcp connection
2. start and close of subflows (joins)
3. announce and withdrawals of addresses
4. subflow priority (backup/non-backup) change.

Reviewed-by: Matthieu Baerts <[email protected]>
Reviewed-by: Mat Martineau <[email protected]>
Signed-off-by: Florian Westphal <[email protected]>

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/pm.c

@@ -75,6 +75,7 @@ void mptcp_pm_new_connection(struct mptcp_sock *msk, const struct sock *ssk, int
 	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)
@@ -122,13 +123,10 @@ static bool mptcp_pm_schedule_work(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, const struct sock *ssk,
 	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 */