Merge branch 'mptcp-userspace-path-manager-prerequisites'

Mat Martineau says:

====================
mptcp: Userspace path manager prerequisites

This series builds upon the path manager mode selection changes merged
in 4994d4fa ("Merge branch 'mptcp-path-manager-mode-selection'") to
further modify the path manager code in preparation for adding the new
netlink commands to announce/remove advertised addresses and
create/destroy subflows of an MPTCP connection. The third and final
patch series for the userspace path manager will implement those
commands as discussed in
https://lore.kernel.org/netdev/23ff3b49-2563-1874-fa35-3af55d3088e7@linux.intel.com/#r

Patches 1, 5, and 7 remove some internal constraints on path managers
(in general) without changing in-kernel PM behavior.

Patch 2 adds a self test to validate MPTCP address advertisement ack
behavior.

Patches 3, 4, and 6 add new attributes to existing MPTCP netlink events
and track internal state for populating those attributes.
====================

Link: https://lore.kernel.org/r/20220502205237.129297-1-mathew.j.martineau@linux.intel.comSigned-off-by: Jakub Kicinski <kuba@kernel.org>

include/uapi/linux/mptcp.h

@@ -188,6 +188,7 @@ enum mptcp_event_attr {
 	MPTCP_ATTR_IF_IDX,	/* s32 */
 	MPTCP_ATTR_RESET_REASON,/* u32 */
 	MPTCP_ATTR_RESET_FLAGS, /* u32 */
+	MPTCP_ATTR_SERVER_SIDE,	/* u8 */
 
 	__MPTCP_ATTR_AFTER_LAST
 };

net/mptcp/options.c

@@ -931,7 +931,7 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk,
 		if (TCP_SKB_CB(skb)->seq == subflow->ssn_offset + 1 &&
 		    TCP_SKB_CB(skb)->end_seq == TCP_SKB_CB(skb)->seq &&
 		    subflow->mp_join && (mp_opt->suboptions & OPTIONS_MPTCP_MPJ) &&
-		    READ_ONCE(msk->pm.server_side))
+		    !subflow->request_join)
 			tcp_send_ack(ssk);
 		goto fully_established;
 	}
@@ -1133,7 +1133,7 @@ bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
 		if ((mp_opt.suboptions & OPTION_MPTCP_ADD_ADDR) &&
 		    add_addr_hmac_valid(msk, &mp_opt)) {
 			if (!mp_opt.echo) {
-				mptcp_pm_add_addr_received(msk, &mp_opt.addr);
+				mptcp_pm_add_addr_received(sk, &mp_opt.addr);
 				MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ADDADDR);
 			} else {
 				mptcp_pm_add_addr_echoed(msk, &mp_opt.addr);

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,
@@ -179,7 +182,8 @@ void mptcp_pm_subflow_check_next(struct mptcp_sock *msk, const struct sock *ssk,
 	bool update_subflows;
 
 	update_subflows = (ssk->sk_state == TCP_CLOSE) &&
-			  (subflow->request_join || subflow->mp_join);
+			  (subflow->request_join || subflow->mp_join) &&
+			  mptcp_pm_is_kernel(msk);
 	if (!READ_ONCE(pm->work_pending) && !update_subflows)
 		return;
 
@@ -196,19 +200,28 @@ void mptcp_pm_subflow_check_next(struct mptcp_sock *msk, const struct sock *ssk,
 	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) || mptcp_pm_is_userspace(msk)) {
+	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)) {

net/mptcp/pm_netlink.c

@@ -369,8 +369,16 @@ static bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk,
 
 	lockdep_assert_held(&msk->pm.lock);
 
-	if (mptcp_lookup_anno_list_by_saddr(msk, &entry->addr))
-		return false;
+	add_entry = mptcp_lookup_anno_list_by_saddr(msk, &entry->addr);
+
+	if (add_entry) {
+		if (mptcp_pm_is_kernel(msk))
+			return false;
+
+		sk_reset_timer(sk, &add_entry->add_timer,
+			       jiffies + mptcp_get_add_addr_timeout(net));
+		return true;
+	}
 
 	add_entry = kmalloc(sizeof(*add_entry), GFP_ATOMIC);
 	if (!add_entry)
@@ -805,6 +813,9 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk,
 		if (!removed)
 			continue;
 
+		if (!mptcp_pm_is_kernel(msk))
+			continue;
+
 		if (rm_type == MPTCP_MIB_RMADDR) {
 			msk->pm.add_addr_accepted--;
 			WRITE_ONCE(msk->pm.accept_addr, true);
@@ -1855,6 +1866,13 @@ static void mptcp_nl_mcast_send(struct net *net, struct sk_buff *nlskb, gfp_t gf
 				nlskb, 0, MPTCP_PM_EV_GRP_OFFSET, gfp);
 }
 
+bool mptcp_userspace_pm_active(const struct mptcp_sock *msk)
+{
+	return genl_has_listeners(&mptcp_genl_family,
+				  sock_net((const struct sock *)msk),
+				  MPTCP_PM_EV_GRP_OFFSET);
+}
+
 static int mptcp_event_add_subflow(struct sk_buff *skb, const struct sock *ssk)
 {
 	const struct inet_sock *issk = inet_sk(ssk);
@@ -1975,6 +1993,9 @@ static int mptcp_event_created(struct sk_buff *skb,
 	if (err)
 		return err;
 
+	if (nla_put_u8(skb, MPTCP_ATTR_SERVER_SIDE, READ_ONCE(msk->pm.server_side)))
+		return -EMSGSIZE;
+
 	return mptcp_event_add_subflow(skb, ssk);
 }
 
@@ -2009,10 +2030,12 @@ void mptcp_event_addr_removed(const struct mptcp_sock *msk, uint8_t id)
 	kfree_skb(skb);
 }
 
-void mptcp_event_addr_announced(const struct mptcp_sock *msk,
+void mptcp_event_addr_announced(const struct sock *ssk,
 				const struct mptcp_addr_info *info)
 {
-	struct net *net = sock_net((const struct sock *)msk);
+	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
+	struct mptcp_sock *msk = mptcp_sk(subflow->conn);
+	struct net *net = sock_net(ssk);
 	struct nlmsghdr *nlh;
 	struct sk_buff *skb;
 
@@ -2034,7 +2057,10 @@ void mptcp_event_addr_announced(const struct mptcp_sock *msk,
 	if (nla_put_u8(skb, MPTCP_ATTR_REM_ID, info->id))
 		goto nla_put_failure;
 
-	if (nla_put_be16(skb, MPTCP_ATTR_DPORT, info->port))
+	if (nla_put_be16(skb, MPTCP_ATTR_DPORT,
+			 info->port == 0 ?
+			 inet_sk(ssk)->inet_dport :
+			 info->port))
 		goto nla_put_failure;
 
 	switch (info->family) {

net/mptcp/protocol.c

@@ -3321,15 +3321,12 @@ bool mptcp_finish_join(struct sock *ssk)
 		return false;
 	}
 
-	if (!msk->pm.server_side)
+	if (!list_empty(&subflow->node))
 		goto out;
 
 	if (!mptcp_pm_allow_new_subflow(msk))
 		goto err_prohibited;
 
-	if (WARN_ON_ONCE(!list_empty(&subflow->node)))
-		goto err_prohibited;
-
 	/* active connections are already on conn_list.
 	 * If we can't acquire msk socket lock here, let the release callback
 	 * handle it

net/mptcp/protocol.h

@@ -753,7 +753,7 @@ void mptcp_pm_subflow_established(struct mptcp_sock *msk);
 bool mptcp_pm_nl_check_work_pending(struct mptcp_sock *msk);
 void mptcp_pm_subflow_check_next(struct mptcp_sock *msk, const struct sock *ssk,
 				 const struct mptcp_subflow_context *subflow);
-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);
 void mptcp_pm_add_addr_echoed(struct mptcp_sock *msk,
 			      const struct mptcp_addr_info *addr);
@@ -782,8 +782,9 @@ int mptcp_pm_remove_subflow(struct mptcp_sock *msk, const struct mptcp_rm_list *
 
 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_announced(const struct sock *ssk, const struct mptcp_addr_info *info);
 void mptcp_event_addr_removed(const struct mptcp_sock *msk, u8 id);
+bool mptcp_userspace_pm_active(const struct mptcp_sock *msk);
 
 static inline bool mptcp_pm_should_add_signal(struct mptcp_sock *msk)
 {
@@ -811,6 +812,11 @@ static inline bool mptcp_pm_is_userspace(const struct mptcp_sock *msk)
 	return READ_ONCE(msk->pm.pm_type) == MPTCP_PM_TYPE_USERSPACE;
 }
 
+static inline bool mptcp_pm_is_kernel(const struct mptcp_sock *msk)
+{
+	return READ_ONCE(msk->pm.pm_type) == MPTCP_PM_TYPE_KERNEL;
+}
+
 static inline unsigned int mptcp_add_addr_len(int family, bool echo, bool port)
 {
 	u8 len = TCPOLEN_MPTCP_ADD_ADDR_BASE;
@@ -905,13 +911,17 @@ static inline bool mptcp_check_infinite_map(struct sk_buff *skb)
 	return false;
 }
 
+static inline bool is_active_ssk(struct mptcp_subflow_context *subflow)
+{
+	return (subflow->request_mptcp || subflow->request_join);
+}
+
 static inline bool subflow_simultaneous_connect(struct sock *sk)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
-	struct sock *parent = subflow->conn;
 
 	return sk->sk_state == TCP_ESTABLISHED &&
-	       !mptcp_sk(parent)->pm.server_side &&
+	       is_active_ssk(subflow) &&
 	       !subflow->conn_finished;
 }
 

net/mptcp/subflow.c

@@ -62,7 +62,9 @@ static void subflow_generate_hmac(u64 key1, u64 key2, u32 nonce1, u32 nonce2,
 static bool mptcp_can_accept_new_subflow(const struct mptcp_sock *msk)
 {
 	return mptcp_is_fully_established((void *)msk) &&
-	       READ_ONCE(msk->pm.accept_subflow);
+		((mptcp_pm_is_userspace(msk) &&
+		  mptcp_userspace_pm_active(msk)) ||
+		 READ_ONCE(msk->pm.accept_subflow));
 }
 
 /* validate received token and create truncated hmac and nonce for SYN-ACK */
@@ -441,6 +443,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 		subflow->backup = mp_opt.backup;
 		subflow->thmac = mp_opt.thmac;
 		subflow->remote_nonce = mp_opt.nonce;
+		subflow->remote_id = mp_opt.join_id;
 		pr_debug("subflow=%p, thmac=%llu, remote_nonce=%u backup=%d",
 			 subflow, subflow->thmac, subflow->remote_nonce,
 			 subflow->backup);

tools/testing/selftests/net/mptcp/mptcp_join.sh

@@ -2719,6 +2719,17 @@ userspace_tests()
 		chk_add_nr 0 0
 	fi
 
+	# userspace pm type does not echo add_addr without daemon
+	if reset "userspace pm no echo w/o daemon"; then
+		set_userspace_pm $ns2
+		pm_nl_set_limits $ns1 0 2
+		pm_nl_set_limits $ns2 0 2
+		pm_nl_add_endpoint $ns1 10.0.2.1 flags signal
+		run_tests $ns1 $ns2 10.0.1.1
+		chk_join_nr 0 0 0
+		chk_add_nr 1 0
+	fi
+
 	# userspace pm type rejects join
 	if reset "userspace pm type rejects join"; then
 		set_userspace_pm $ns1