Merge branch 'mptcp-support-changes-to-initial-subflow-priority'

Mat Martineau says:

====================
mptcp: Support changes to initial subflow priority

This series updates the in-kernel MPTCP path manager to allow changes to
subflow priority for the first subflow created for each MPTCP connection
(the one created with the MP_CAPABLE handshake).

Patches 1 and 2 do some refactoring to simplify the new functionality.

Patch 3 introduces the new feature to change the initial subflow
priority and send the MP_PRIO header on that subflow.

Patch 4 cleans up code related to tracking endpoint ids on the initial
subflow.

Patch 5 adds a selftest to confirm that subflow priorities are updated
as expected.
====================

Link: https://lore.kernel.org/r/20220711191633.80826-1-mathew.j.martineau@linux.intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

4 files changed, 105 insertions, 58 deletions

diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 5bdb559d5242..291b5da42fdb 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -413,7 +413,7 @@ static bool lookup_address_in_vec(const struct mptcp_addr_info *addrs, unsigned
 	int i;
 
 	for (i = 0; i < nr; i++) {
-		if (mptcp_addresses_equal(&addrs[i], addr, addr->port))
+		if (addrs[i].id == addr->id)
 			return true;
 	}
 
@@ -449,7 +449,8 @@ static unsigned int fill_remote_addresses_vec(struct mptcp_sock *msk, bool fullm
 		mptcp_for_each_subflow(msk, subflow) {
 			ssk = mptcp_subflow_tcp_sock(subflow);
 			remote_address((struct sock_common *)ssk, &addrs[i]);
-			if (deny_id0 && mptcp_addresses_equal(&addrs[i], &remote, false))
+			addrs[i].id = subflow->remote_id;
+			if (deny_id0 && !addrs[i].id)
 				continue;
 
 			if (!lookup_address_in_vec(addrs, i, &addrs[i]) &&
@@ -463,6 +464,37 @@ static unsigned int fill_remote_addresses_vec(struct mptcp_sock *msk, bool fullm
 	return i;
 }
 
+static void __mptcp_pm_send_ack(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow,
+				bool prio, bool backup)
+{
+	struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+	bool slow;
+
+	pr_debug("send ack for %s",
+		 prio ? "mp_prio" : (mptcp_pm_should_add_signal(msk) ? "add_addr" : "rm_addr"));
+
+	slow = lock_sock_fast(ssk);
+	if (prio) {
+		if (subflow->backup != backup)
+			msk->last_snd = NULL;
+
+		subflow->send_mp_prio = 1;
+		subflow->backup = backup;
+		subflow->request_bkup = backup;
+	}
+
+	__mptcp_subflow_send_ack(ssk);
+	unlock_sock_fast(ssk, slow);
+}
+
+static void mptcp_pm_send_ack(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow,
+			      bool prio, bool backup)
+{
+	spin_unlock_bh(&msk->pm.lock);
+	__mptcp_pm_send_ack(msk, subflow, prio, backup);
+	spin_lock_bh(&msk->pm.lock);
+}
+
 static struct mptcp_pm_addr_entry *
 __lookup_addr_by_id(struct pm_nl_pernet *pernet, unsigned int id)
 {
@@ -482,30 +514,14 @@ __lookup_addr(struct pm_nl_pernet *pernet, const struct mptcp_addr_info *info,
 	struct mptcp_pm_addr_entry *entry;
 
 	list_for_each_entry(entry, &pernet->local_addr_list, list) {
-		if ((!lookup_by_id && mptcp_addresses_equal(&entry->addr, info, true)) ||
+		if ((!lookup_by_id &&
+		     mptcp_addresses_equal(&entry->addr, info, entry->addr.port)) ||
 		    (lookup_by_id && entry->addr.id == info->id))
 			return entry;
 	}
 	return NULL;
 }
 
-static int
-lookup_id_by_addr(const struct pm_nl_pernet *pernet, const struct mptcp_addr_info *addr)
-{
-	const struct mptcp_pm_addr_entry *entry;
-	int ret = -1;
-
-	rcu_read_lock();
-	list_for_each_entry(entry, &pernet->local_addr_list, list) {
-		if (mptcp_addresses_equal(&entry->addr, addr, entry->addr.port)) {
-			ret = entry->addr.id;
-			break;
-		}
-	}
-	rcu_read_unlock();
-	return ret;
-}
-
 static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
 {
 	struct sock *sk = (struct sock *)msk;
@@ -523,13 +539,23 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
 
 	/* do lazy endpoint usage accounting for the MPC subflows */
 	if (unlikely(!(msk->pm.status & BIT(MPTCP_PM_MPC_ENDPOINT_ACCOUNTED))) && msk->first) {
+		struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(msk->first);
+		struct mptcp_pm_addr_entry *entry;
 		struct mptcp_addr_info mpc_addr;
-		int mpc_id;
+		bool backup = false;
 
 		local_address((struct sock_common *)msk->first, &mpc_addr);
-		mpc_id = lookup_id_by_addr(pernet, &mpc_addr);
-		if (mpc_id >= 0)
-			__clear_bit(mpc_id, msk->pm.id_avail_bitmap);
+		rcu_read_lock();
+		entry = __lookup_addr(pernet, &mpc_addr, false);
+		if (entry) {
+			__clear_bit(entry->addr.id, msk->pm.id_avail_bitmap);
+			msk->mpc_endpoint_id = entry->addr.id;
+			backup = !!(entry->flags & MPTCP_PM_ADDR_FLAG_BACKUP);
+		}
+		rcu_read_unlock();
+
+		if (backup)
+			mptcp_pm_send_ack(msk, subflow, true, backup);
 
 		msk->pm.status |= BIT(MPTCP_PM_MPC_ENDPOINT_ACCOUNTED);
 	}
@@ -705,16 +731,8 @@ void mptcp_pm_nl_addr_send_ack(struct mptcp_sock *msk)
 		return;
 
 	subflow = list_first_entry_or_null(&msk->conn_list, typeof(*subflow), node);
-	if (subflow) {
-		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
-
-		spin_unlock_bh(&msk->pm.lock);
-		pr_debug("send ack for %s",
-			 mptcp_pm_should_add_signal(msk) ? "add_addr" : "rm_addr");
-
-		mptcp_subflow_send_ack(ssk);
-		spin_lock_bh(&msk->pm.lock);
-	}
+	if (subflow)
+		mptcp_pm_send_ack(msk, subflow, false, false);
 }
 
 int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk,
@@ -729,7 +747,6 @@ int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk,
 	mptcp_for_each_subflow(msk, subflow) {
 		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
 		struct mptcp_addr_info local, remote;
-		bool slow;
 
 		local_address((struct sock_common *)ssk, &local);
 		if (!mptcp_addresses_equal(&local, addr, addr->port))
@@ -741,23 +758,18 @@ int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk,
 				continue;
 		}
 
-		slow = lock_sock_fast(ssk);
-		if (subflow->backup != bkup)
-			msk->last_snd = NULL;
-		subflow->backup = bkup;
-		subflow->send_mp_prio = 1;
-		subflow->request_bkup = bkup;
-
-		pr_debug("send ack for mp_prio");
-		__mptcp_subflow_send_ack(ssk);
-		unlock_sock_fast(ssk, slow);
-
+		__mptcp_pm_send_ack(msk, subflow, true, bkup);
 		return 0;
 	}
 
 	return -EINVAL;
 }
 
+static bool mptcp_local_id_match(const struct mptcp_sock *msk, u8 local_id, u8 id)
+{
+	return local_id == id || (!local_id && msk->mpc_endpoint_id == id);
+}
+
 static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk,
 					   const struct mptcp_rm_list *rm_list,
 					   enum linux_mptcp_mib_field rm_type)
@@ -781,6 +793,7 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk,
 		return;
 
 	for (i = 0; i < rm_list->nr; i++) {
+		u8 rm_id = rm_list->ids[i];
 		bool removed = false;
 
 		list_for_each_entry_safe(subflow, tmp, &msk->conn_list, node) {
@@ -788,15 +801,15 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk,
 			int how = RCV_SHUTDOWN | SEND_SHUTDOWN;
 			u8 id = subflow->local_id;
 
-			if (rm_type == MPTCP_MIB_RMADDR)
-				id = subflow->remote_id;
-
-			if (rm_list->ids[i] != id)
+			if (rm_type == MPTCP_MIB_RMADDR && subflow->remote_id != rm_id)
+				continue;
+			if (rm_type == MPTCP_MIB_RMSUBFLOW && !mptcp_local_id_match(msk, id, rm_id))
 				continue;
 
-			pr_debug(" -> %s rm_list_ids[%d]=%u local_id=%u remote_id=%u",
+			pr_debug(" -> %s rm_list_ids[%d]=%u local_id=%u remote_id=%u mpc_id=%u",
 				 rm_type == MPTCP_MIB_RMADDR ? "address" : "subflow",
-				 i, rm_list->ids[i], subflow->local_id, subflow->remote_id);
+				 i, rm_id, subflow->local_id, subflow->remote_id,
+				 msk->mpc_endpoint_id);
 			spin_unlock_bh(&msk->pm.lock);
 			mptcp_subflow_shutdown(sk, ssk, how);
 
@@ -808,7 +821,7 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk,
 			__MPTCP_INC_STATS(sock_net(sk), rm_type);
 		}
 		if (rm_type == MPTCP_MIB_RMSUBFLOW)
-			__set_bit(rm_list->ids[i], msk->pm.id_avail_bitmap);
+			__set_bit(rm_id ? rm_id : msk->mpc_endpoint_id, msk->pm.id_avail_bitmap);
 		if (!removed)
 			continue;
 
@@ -907,10 +920,11 @@ static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet,
 	/* do not insert duplicate address, differentiate on port only
 	 * singled addresses
 	 */
+	if (!address_use_port(entry))
+		entry->addr.port = 0;
 	list_for_each_entry(cur, &pernet->local_addr_list, list) {
 		if (mptcp_addresses_equal(&cur->addr, &entry->addr,
-					  address_use_port(entry) &&
-					  address_use_port(cur))) {
+					  cur->addr.port || entry->addr.port)) {
 			/* allow replacing the exiting endpoint only if such
 			 * endpoint is an implicit one and the user-space
 			 * did not provide an endpoint id
@@ -956,7 +970,10 @@ find_next:
 	}
 
 	pernet->addrs++;
-	list_add_tail_rcu(&entry->list, &pernet->local_addr_list);
+	if (!entry->addr.port)
+		list_add_tail_rcu(&entry->list, &pernet->local_addr_list);
+	else
+		list_add_rcu(&entry->list, &pernet->local_addr_list);
 	ret = entry->addr.id;
 
 out:
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 2caad4a3adea..6cf5fa191b12 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -508,7 +508,7 @@ void __mptcp_subflow_send_ack(struct sock *ssk)
 		tcp_send_ack(ssk);
 }
 
-void mptcp_subflow_send_ack(struct sock *ssk)
+static void mptcp_subflow_send_ack(struct sock *ssk)
 {
 	bool slow;
 
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 07871e10e510..5d6043c16b09 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -282,6 +282,7 @@ struct mptcp_sock {
 	bool		use_64bit_ack; /* Set when we received a 64-bit DSN */
 	bool		csum_enabled;
 	bool		allow_infinite_fallback;
+	u8		mpc_endpoint_id;
 	u8		recvmsg_inq:1,
 			cork:1,
 			nodelay:1;
@@ -607,7 +608,6 @@ void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how);
 void mptcp_close_ssk(struct sock *sk, struct sock *ssk,
 		     struct mptcp_subflow_context *subflow);
 void __mptcp_subflow_send_ack(struct sock *ssk);
-void mptcp_subflow_send_ack(struct sock *ssk);
 void mptcp_subflow_reset(struct sock *ssk);
 void mptcp_subflow_queue_clean(struct sock *ssk);
 void mptcp_sock_graft(struct sock *sk, struct socket *parent);
diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 55efe2aafb84..ff83ef426df5 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -2428,6 +2428,36 @@ backup_tests()
 		chk_add_nr 1 1
 		chk_prio_nr 1 1
 	fi
+
+	if reset "mpc backup"; then
+		pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow,backup
+		run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow
+		chk_join_nr 0 0 0
+		chk_prio_nr 0 1
+	fi
+
+	if reset "mpc backup both sides"; then
+		pm_nl_add_endpoint $ns1 10.0.1.1 flags subflow,backup
+		pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow,backup
+		run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow
+		chk_join_nr 0 0 0
+		chk_prio_nr 1 1
+	fi
+
+	if reset "mpc switch to backup"; then
+		pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow
+		run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow backup
+		chk_join_nr 0 0 0
+		chk_prio_nr 0 1
+	fi
+
+	if reset "mpc switch to backup both sides"; then
+		pm_nl_add_endpoint $ns1 10.0.1.1 flags subflow
+		pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow
+		run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow backup
+		chk_join_nr 0 0 0
+		chk_prio_nr 1 1
+	fi
 }
 
 add_addr_ports_tests()