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 <[email protected]>

Author: davem330

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 */