1 files changed, 121 insertions, 31 deletions

diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index 6ab386ff3294..45e2a48397b9 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -87,6 +87,9 @@ bool mptcp_pm_allow_new_subflow(struct mptcp_sock *msk)
 	unsigned int subflows_max;
 	int ret = 0;
 
+	if (mptcp_pm_is_userspace(msk))
+		return mptcp_userspace_pm_active(msk);
+
 	subflows_max = mptcp_pm_get_subflows_max(msk);
 
 	pr_debug("msk=%p subflows=%d max=%d allow=%d", msk, pm->subflows,
@@ -172,35 +175,65 @@ void mptcp_pm_subflow_established(struct mptcp_sock *msk)
 	spin_unlock_bh(&pm->lock);
 }
 
-void mptcp_pm_subflow_closed(struct mptcp_sock *msk, u8 id)
+void mptcp_pm_subflow_check_next(struct mptcp_sock *msk, const struct sock *ssk,
+				 const struct mptcp_subflow_context *subflow)
 {
-	pr_debug("msk=%p", msk);
+	struct mptcp_pm_data *pm = &msk->pm;
+	bool update_subflows;
+
+	update_subflows = (subflow->request_join || subflow->mp_join) &&
+			  mptcp_pm_is_kernel(msk);
+	if (!READ_ONCE(pm->work_pending) && !update_subflows)
+		return;
+
+	spin_lock_bh(&pm->lock);
+	if (update_subflows)
+		__mptcp_pm_close_subflow(msk);
+
+	/* Even if this subflow is not really established, tell the PM to try
+	 * to pick the next ones, if possible.
+	 */
+	if (mptcp_pm_nl_check_work_pending(msk))
+		mptcp_pm_schedule_work(msk, MPTCP_PM_SUBFLOW_ESTABLISHED);
+
+	spin_unlock_bh(&pm->lock);
 }
 
-void mptcp_pm_add_addr_received(struct mptcp_sock *msk,
+void mptcp_pm_add_addr_received(const struct sock *ssk,
 				const struct mptcp_addr_info *addr)
 {
+	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
+	struct mptcp_sock *msk = mptcp_sk(subflow->conn);
 	struct mptcp_pm_data *pm = &msk->pm;
 
 	pr_debug("msk=%p remote_id=%d accept=%d", msk, addr->id,
 		 READ_ONCE(pm->accept_addr));
 
-	mptcp_event_addr_announced(msk, addr);
+	mptcp_event_addr_announced(ssk, addr);
 
 	spin_lock_bh(&pm->lock);
 
-	if (!READ_ONCE(pm->accept_addr)) {
+	if (mptcp_pm_is_userspace(msk)) {
+		if (mptcp_userspace_pm_active(msk)) {
+			mptcp_pm_announce_addr(msk, addr, true);
+			mptcp_pm_add_addr_send_ack(msk);
+		} else {
+			__MPTCP_INC_STATS(sock_net((struct sock *)msk), MPTCP_MIB_ADDADDRDROP);
+		}
+	} else if (!READ_ONCE(pm->accept_addr)) {
 		mptcp_pm_announce_addr(msk, addr, true);
 		mptcp_pm_add_addr_send_ack(msk);
 	} else if (mptcp_pm_schedule_work(msk, MPTCP_PM_ADD_ADDR_RECEIVED)) {
 		pm->remote = *addr;
+	} else {
+		__MPTCP_INC_STATS(sock_net((struct sock *)msk), MPTCP_MIB_ADDADDRDROP);
 	}
 
 	spin_unlock_bh(&pm->lock);
 }
 
 void mptcp_pm_add_addr_echoed(struct mptcp_sock *msk,
-			      struct mptcp_addr_info *addr)
+			      const struct mptcp_addr_info *addr)
 {
 	struct mptcp_pm_data *pm = &msk->pm;
 
@@ -234,36 +267,67 @@ void mptcp_pm_rm_addr_received(struct mptcp_sock *msk,
 		mptcp_event_addr_removed(msk, rm_list->ids[i]);
 
 	spin_lock_bh(&pm->lock);
-	mptcp_pm_schedule_work(msk, MPTCP_PM_RM_ADDR_RECEIVED);
-	pm->rm_list_rx = *rm_list;
+	if (mptcp_pm_schedule_work(msk, MPTCP_PM_RM_ADDR_RECEIVED))
+		pm->rm_list_rx = *rm_list;
+	else
+		__MPTCP_INC_STATS(sock_net((struct sock *)msk), MPTCP_MIB_RMADDRDROP);
 	spin_unlock_bh(&pm->lock);
 }
 
-void mptcp_pm_mp_prio_received(struct sock *sk, u8 bkup)
+void mptcp_pm_mp_prio_received(struct sock *ssk, u8 bkup)
 {
-	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
+	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
+	struct sock *sk = subflow->conn;
+	struct mptcp_sock *msk;
 
 	pr_debug("subflow->backup=%d, bkup=%d\n", subflow->backup, bkup);
-	subflow->backup = bkup;
+	msk = mptcp_sk(sk);
+	if (subflow->backup != bkup) {
+		subflow->backup = bkup;
+		mptcp_data_lock(sk);
+		if (!sock_owned_by_user(sk))
+			msk->last_snd = NULL;
+		else
+			__set_bit(MPTCP_RESET_SCHEDULER,  &msk->cb_flags);
+		mptcp_data_unlock(sk);
+	}
 
-	mptcp_event(MPTCP_EVENT_SUB_PRIORITY, mptcp_sk(subflow->conn), sk, GFP_ATOMIC);
+	mptcp_event(MPTCP_EVENT_SUB_PRIORITY, msk, ssk, GFP_ATOMIC);
 }
 
 void mptcp_pm_mp_fail_received(struct sock *sk, u64 fail_seq)
 {
+	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
+	struct mptcp_sock *msk = mptcp_sk(subflow->conn);
+
 	pr_debug("fail_seq=%llu", fail_seq);
+
+	if (!READ_ONCE(msk->allow_infinite_fallback))
+		return;
+
+	if (!subflow->fail_tout) {
+		pr_debug("send MP_FAIL response and infinite map");
+
+		subflow->send_mp_fail = 1;
+		subflow->send_infinite_map = 1;
+		tcp_send_ack(sk);
+	} else {
+		pr_debug("MP_FAIL response received");
+		WRITE_ONCE(subflow->fail_tout, 0);
+	}
 }
 
 /* path manager helpers */
 
-bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, struct sk_buff *skb,
+bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, const struct sk_buff *skb,
 			      unsigned int opt_size, unsigned int remaining,
 			      struct mptcp_addr_info *addr, bool *echo,
-			      bool *port, bool *drop_other_suboptions)
+			      bool *drop_other_suboptions)
 {
 	int ret = false;
 	u8 add_addr;
 	u8 family;
+	bool port;
 
 	spin_lock_bh(&msk->pm.lock);
 
@@ -281,10 +345,10 @@ bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, struct sk_buff *skb,
 	}
 
 	*echo = mptcp_pm_should_add_signal_echo(msk);
-	*port = !!(*echo ? msk->pm.remote.port : msk->pm.local.port);
+	port = !!(*echo ? msk->pm.remote.port : msk->pm.local.port);
 
 	family = *echo ? msk->pm.remote.family : msk->pm.local.family;
-	if (remaining < mptcp_add_addr_len(family, *echo, *port))
+	if (remaining < mptcp_add_addr_len(family, *echo, port))
 		goto out_unlock;
 
 	if (*echo) {
@@ -356,25 +420,51 @@ void mptcp_pm_subflow_chk_stale(const struct mptcp_sock *msk, struct sock *ssk)
 	}
 }
 
-void mptcp_pm_data_init(struct mptcp_sock *msk)
+void mptcp_pm_data_reset(struct mptcp_sock *msk)
 {
-	msk->pm.add_addr_signaled = 0;
-	msk->pm.add_addr_accepted = 0;
-	msk->pm.local_addr_used = 0;
-	msk->pm.subflows = 0;
-	msk->pm.rm_list_tx.nr = 0;
-	msk->pm.rm_list_rx.nr = 0;
-	WRITE_ONCE(msk->pm.work_pending, false);
-	WRITE_ONCE(msk->pm.addr_signal, 0);
-	WRITE_ONCE(msk->pm.accept_addr, false);
-	WRITE_ONCE(msk->pm.accept_subflow, false);
-	WRITE_ONCE(msk->pm.remote_deny_join_id0, false);
-	msk->pm.status = 0;
+	u8 pm_type = mptcp_get_pm_type(sock_net((struct sock *)msk));
+	struct mptcp_pm_data *pm = &msk->pm;
 
+	pm->add_addr_signaled = 0;
+	pm->add_addr_accepted = 0;
+	pm->local_addr_used = 0;
+	pm->subflows = 0;
+	pm->rm_list_tx.nr = 0;
+	pm->rm_list_rx.nr = 0;
+	WRITE_ONCE(pm->pm_type, pm_type);
+
+	if (pm_type == MPTCP_PM_TYPE_KERNEL) {
+		bool subflows_allowed = !!mptcp_pm_get_subflows_max(msk);
+
+		/* pm->work_pending must be only be set to 'true' when
+		 * pm->pm_type is set to MPTCP_PM_TYPE_KERNEL
+		 */
+		WRITE_ONCE(pm->work_pending,
+			   (!!mptcp_pm_get_local_addr_max(msk) &&
+			    subflows_allowed) ||
+			   !!mptcp_pm_get_add_addr_signal_max(msk));
+		WRITE_ONCE(pm->accept_addr,
+			   !!mptcp_pm_get_add_addr_accept_max(msk) &&
+			   subflows_allowed);
+		WRITE_ONCE(pm->accept_subflow, subflows_allowed);
+	} else {
+		WRITE_ONCE(pm->work_pending, 0);
+		WRITE_ONCE(pm->accept_addr, 0);
+		WRITE_ONCE(pm->accept_subflow, 0);
+	}
+
+	WRITE_ONCE(pm->addr_signal, 0);
+	WRITE_ONCE(pm->remote_deny_join_id0, false);
+	pm->status = 0;
+	bitmap_fill(msk->pm.id_avail_bitmap, MPTCP_PM_MAX_ADDR_ID + 1);
+}
+
+void mptcp_pm_data_init(struct mptcp_sock *msk)
+{
 	spin_lock_init(&msk->pm.lock);
 	INIT_LIST_HEAD(&msk->pm.anno_list);
-
-	mptcp_pm_nl_data_init(msk);
+	INIT_LIST_HEAD(&msk->pm.userspace_pm_local_addr_list);
+	mptcp_pm_data_reset(msk);
 }
 
 void __init mptcp_pm_init(void)