diff mbox series

[net-next,7/9] net: dsa: allow masters to join a LAG

Message ID 20220830195932.683432-8-vladimir.oltean@nxp.com (mailing list archive)
State Superseded
Delegated to: Netdev Maintainers
Headers show
Series DSA changes for multiple CPU ports (part 4) | expand

Checks

Context Check Description
netdev/tree_selection success Clearly marked for net-next, async
netdev/fixes_present success Fixes tag not required for -next series
netdev/subject_prefix success Link
netdev/cover_letter success Series has a cover letter
netdev/patch_count success Link
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 21 this patch: 20
netdev/cc_maintainers warning 3 maintainers not CCed: linux-arm-kernel@lists.infradead.org matthias.bgg@gmail.com linux-mediatek@lists.infradead.org
netdev/build_clang success Errors and warnings before: 15 this patch: 13
netdev/module_param success Was 0 now: 0
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn success Errors and warnings before: 21 this patch: 20
netdev/checkpatch warning WARNING: memory barrier without comment
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/source_inline success Was 0 now: 0

Commit Message

Vladimir Oltean Aug. 30, 2022, 7:59 p.m. UTC
There are 2 ways in which a DSA user port may become handled by 2 CPU
ports in a LAG:

(1) its current DSA master joins a LAG

 ip link del bond0 && ip link add bond0 type bond mode 802.3ad
 ip link set eno2 master bond0

When this happens, all user ports with "eno2" as DSA master get
automatically migrated to "bond0" as DSA master.

(2) it is explicitly configured as such by the user

 # Before, the DSA master was eno3
 ip link set swp0 type dsa master bond0

The design of this configuration is that the LAG device dynamically
becomes a DSA master through dsa_master_setup() when the first physical
DSA master becomes a LAG slave, and stops being so through
dsa_master_teardown() when the last physical DSA master leaves.

A LAG interface is considered as a valid DSA master only if it contains
existing DSA masters, and no other lower interfaces. Therefore, we
mainly rely on method (1) to enter this configuration.

Each physical DSA master (LAG slave) retains its dev->dsa_ptr for when
it becomes a standalone DSA master again. But the LAG master also has a
dev->dsa_ptr, and this is actually duplicated from one of the physical
LAG slaves, and therefore needs to be balanced when LAG slaves come and
go.

To the switch driver, putting DSA masters in a LAG is seen as putting
their associated CPU ports in a LAG.

We need to prepare cross-chip host FDB notifiers for CPU ports in a LAG,
by calling the driver's ->lag_fdb_add method rather than ->port_fdb_add.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
---
 include/net/dsa.h  |   6 ++
 net/dsa/dsa_priv.h |   5 ++
 net/dsa/master.c   |  59 +++++++++++++++++
 net/dsa/port.c     |   2 +-
 net/dsa/slave.c    | 157 +++++++++++++++++++++++++++++++++++++++++++--
 net/dsa/switch.c   |  22 +++++--
 6 files changed, 242 insertions(+), 9 deletions(-)
diff mbox series

Patch

diff --git a/include/net/dsa.h b/include/net/dsa.h
index 3f717c3fcba0..53de8effad60 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -300,6 +300,9 @@  struct dsa_port {
 	u8			master_admin_up:1;
 	u8			master_oper_up:1;
 
+	/* Valid only on user ports */
+	u8			cpu_port_in_lag:1;
+
 	u8			setup:1;
 
 	struct device_node	*dn;
@@ -724,6 +727,9 @@  static inline bool dsa_port_offloads_lag(struct dsa_port *dp,
 
 static inline struct net_device *dsa_port_to_master(const struct dsa_port *dp)
 {
+	if (dp->cpu_port_in_lag)
+		return dsa_port_lag_dev_get(dp->cpu_dp);
+
 	return dp->cpu_dp->master;
 }
 
diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h
index d252a04ed725..5628cd5665b0 100644
--- a/net/dsa/dsa_priv.h
+++ b/net/dsa/dsa_priv.h
@@ -184,6 +184,11 @@  static inline int dsa_tag_protocol_overhead(const struct dsa_device_ops *ops)
 /* master.c */
 int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp);
 void dsa_master_teardown(struct net_device *dev);
+int dsa_master_lag_setup(struct net_device *lag_dev, struct dsa_port *cpu_dp,
+			 struct netdev_lag_upper_info *uinfo,
+			 struct netlink_ext_ack *extack);
+void dsa_master_lag_teardown(struct net_device *lag_dev,
+			     struct dsa_port *cpu_dp);
 
 static inline struct net_device *dsa_master_find_slave(struct net_device *dev,
 						       int device, int port)
diff --git a/net/dsa/master.c b/net/dsa/master.c
index 2176c14b97a8..9a15135f72db 100644
--- a/net/dsa/master.c
+++ b/net/dsa/master.c
@@ -428,3 +428,62 @@  void dsa_master_teardown(struct net_device *dev)
 	 */
 	wmb();
 }
+
+int dsa_master_lag_setup(struct net_device *lag_dev, struct dsa_port *cpu_dp,
+			 struct netdev_lag_upper_info *uinfo,
+			 struct netlink_ext_ack *extack)
+{
+	bool master_setup = false;
+	struct net_device *lower;
+	struct list_head *iter;
+	int err;
+
+	/* To be eligible as a DSA master, a LAG must have all lower
+	 * interfaces be eligible DSA masters.
+	 */
+	netdev_for_each_lower_dev(lag_dev, lower, iter) {
+		if (!netdev_uses_dsa(lower)) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "All LAG ports must be eligible as DSA masters");
+			return -EINVAL;
+		}
+	}
+
+	if (!netdev_uses_dsa(lag_dev)) {
+		err = dsa_master_setup(lag_dev, cpu_dp);
+		if (err)
+			return err;
+	}
+
+	err = dsa_port_lag_join(cpu_dp, lag_dev, uinfo, extack);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "CPU port failed to join LAG");
+		goto out_master_teardown;
+	}
+
+	return 0;
+
+out_master_teardown:
+	if (master_setup)
+		dsa_master_teardown(lag_dev);
+	return err;
+}
+
+/* Tear down a master if there isn't any other user port on it,
+ * optionally also destroying LAG information.
+ */
+void dsa_master_lag_teardown(struct net_device *lag_dev,
+			     struct dsa_port *cpu_dp)
+{
+	struct net_device *upper;
+	struct list_head *iter;
+
+	dsa_port_lag_leave(cpu_dp, lag_dev);
+
+	netdev_for_each_upper_dev_rcu(lag_dev, upper, iter)
+		if (dsa_slave_dev_check(upper))
+			return;
+
+	dsa_master_teardown(lag_dev);
+}
diff --git a/net/dsa/port.c b/net/dsa/port.c
index b719763fe97d..d152f7c7eb6d 100644
--- a/net/dsa/port.c
+++ b/net/dsa/port.c
@@ -1392,6 +1392,7 @@  static int dsa_port_assign_master(struct dsa_port *dp,
 		return err;
 
 	dp->cpu_dp = master->dsa_ptr;
+	dp->cpu_port_in_lag = netif_is_lag_master(master);
 
 	return 0;
 }
@@ -1411,7 +1412,6 @@  int dsa_port_change_master(struct dsa_port *dp, struct net_device *master,
 	struct net_device *old_master = dsa_port_to_master(dp);
 	struct net_device *dev = dp->slave;
 	struct dsa_switch *ds = dp->ds;
-	int port = dp->index;
 	bool vlan_filtering;
 	int err, tmp;
 
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 00df6cf07866..1030988d797f 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -2840,6 +2840,10 @@  dsa_master_prechangeupper_sanity_check(struct net_device *master,
 	if (netif_is_bridge_master(info->upper_dev))
 		return NOTIFY_DONE;
 
+	/* Allow LAG uppers */
+	if (netif_is_lag_master(info->upper_dev))
+		return NOTIFY_DONE;
+
 	extack = netdev_notifier_info_to_extack(&info->info);
 
 	NL_SET_ERR_MSG_MOD(extack,
@@ -2887,6 +2891,138 @@  dsa_bridge_prechangelower_sanity_check(struct net_device *new_lower,
 	return NOTIFY_DONE;
 }
 
+static void dsa_tree_migrate_ports_from_lag_master(struct dsa_switch_tree *dst,
+						   struct net_device *lag_dev)
+{
+	struct net_device *new_master;
+	struct dsa_port *dp;
+	int err;
+
+	new_master = dsa_tree_find_first_master(dst);
+
+	dsa_tree_for_each_user_port(dp, dst) {
+		if (dsa_port_to_master(dp) != lag_dev)
+			continue;
+
+		err = dsa_slave_change_master(dp->slave, new_master, NULL);
+		if (err) {
+			netdev_err(dp->slave,
+				   "failed to restore master to %s: %pe\n",
+				   new_master->name, ERR_PTR(err));
+		}
+	}
+}
+
+static int dsa_master_lag_join(struct net_device *master,
+			       struct net_device *lag_dev,
+			       struct netdev_lag_upper_info *uinfo,
+			       struct netlink_ext_ack *extack)
+{
+	struct dsa_port *cpu_dp = master->dsa_ptr;
+	struct dsa_switch_tree *dst = cpu_dp->dst;
+	struct dsa_port *dp;
+	int err;
+
+	err = dsa_master_lag_setup(lag_dev, cpu_dp, uinfo, extack);
+	if (err)
+		return err;
+
+	dsa_tree_for_each_user_port(dp, dst) {
+		if (dsa_port_to_master(dp) != master)
+			continue;
+
+		err = dsa_slave_change_master(dp->slave, lag_dev, extack);
+		if (err)
+			goto restore;
+	}
+
+	return 0;
+
+restore:
+	dsa_tree_for_each_user_port_continue_reverse(dp, dst) {
+		if (dsa_port_to_master(dp) != lag_dev)
+			continue;
+
+		err = dsa_slave_change_master(dp->slave, master, NULL);
+		if (err) {
+			netdev_err(dp->slave,
+				   "failed to restore master to %s: %pe\n",
+				   master->name, ERR_PTR(err));
+		}
+	}
+
+	dsa_master_lag_teardown(lag_dev, master->dsa_ptr);
+
+	return err;
+}
+
+static void dsa_master_lag_leave(struct net_device *master,
+				 struct net_device *lag_dev)
+{
+	struct dsa_port *dp, *cpu_dp = lag_dev->dsa_ptr;
+	struct dsa_switch_tree *dst = cpu_dp->dst;
+	struct dsa_port *new_cpu_dp = NULL;
+	struct net_device *lower;
+	struct list_head *iter;
+
+	netdev_for_each_lower_dev(lag_dev, lower, iter) {
+		if (netdev_uses_dsa(lower)) {
+			new_cpu_dp = lower->dsa_ptr;
+			break;
+		}
+	}
+
+	if (new_cpu_dp) {
+		/* Update the CPU port of the user ports still under the LAG
+		 * so that dsa_port_to_master() continues to work properly
+		 */
+		dsa_tree_for_each_user_port(dp, dst)
+			if (dsa_port_to_master(dp) == lag_dev)
+				dp->cpu_dp = new_cpu_dp;
+
+		/* Update the index of the virtual CPU port to match the lowest
+		 * physical CPU port
+		 */
+		lag_dev->dsa_ptr = new_cpu_dp;
+		wmb();
+	} else {
+		/* If the LAG DSA master has no ports left, migrate back all
+		 * user ports to the first physical CPU port
+		 */
+		dsa_tree_migrate_ports_from_lag_master(dst, lag_dev);
+	}
+
+	/* This DSA master has left its LAG in any case, so let
+	 * the CPU port leave the hardware LAG as well
+	 */
+	dsa_master_lag_teardown(lag_dev, master->dsa_ptr);
+}
+
+static int dsa_master_changeupper(struct net_device *dev,
+				  struct netdev_notifier_changeupper_info *info)
+{
+	struct netlink_ext_ack *extack;
+	int err = NOTIFY_DONE;
+
+	if (!netdev_uses_dsa(dev))
+		return err;
+
+	extack = netdev_notifier_info_to_extack(&info->info);
+
+	if (netif_is_lag_master(info->upper_dev)) {
+		if (info->linking) {
+			err = dsa_master_lag_join(dev, info->upper_dev,
+						  info->upper_info, extack);
+			err = notifier_from_errno(err);
+		} else {
+			dsa_master_lag_leave(dev, info->upper_dev);
+			err = NOTIFY_OK;
+		}
+	}
+
+	return err;
+}
+
 static int dsa_slave_netdevice_event(struct notifier_block *nb,
 				     unsigned long event, void *ptr)
 {
@@ -2930,6 +3066,10 @@  static int dsa_slave_netdevice_event(struct notifier_block *nb,
 		if (notifier_to_errno(err))
 			return err;
 
+		err = dsa_master_changeupper(dev, ptr);
+		if (notifier_to_errno(err))
+			return err;
+
 		break;
 	}
 	case NETDEV_CHANGELOWERSTATE: {
@@ -2937,12 +3077,21 @@  static int dsa_slave_netdevice_event(struct notifier_block *nb,
 		struct dsa_port *dp;
 		int err;
 
-		if (!dsa_slave_dev_check(dev))
-			break;
+		if (dsa_slave_dev_check(dev)) {
+			dp = dsa_slave_to_port(dev);
+
+			err = dsa_port_lag_change(dp, info->lower_state_info);
+		}
 
-		dp = dsa_slave_to_port(dev);
+		/* Mirror LAG port events on DSA masters that are in
+		 * a LAG towards their respective switch CPU ports
+		 */
+		if (netdev_uses_dsa(dev)) {
+			dp = dev->dsa_ptr;
+
+			err = dsa_port_lag_change(dp, info->lower_state_info);
+		}
 
-		err = dsa_port_lag_change(dp, info->lower_state_info);
 		return notifier_from_errno(err);
 	}
 	case NETDEV_CHANGE:
diff --git a/net/dsa/switch.c b/net/dsa/switch.c
index 4dfd68cf61c5..5c2451fe5461 100644
--- a/net/dsa/switch.c
+++ b/net/dsa/switch.c
@@ -398,8 +398,15 @@  static int dsa_switch_host_fdb_add(struct dsa_switch *ds,
 
 	dsa_switch_for_each_port(dp, ds) {
 		if (dsa_port_host_address_match(dp, info->dp)) {
-			err = dsa_port_do_fdb_add(dp, info->addr, info->vid,
-						  info->db);
+			if (dsa_port_is_cpu(dp) && info->dp->cpu_port_in_lag) {
+				err = dsa_switch_do_lag_fdb_add(ds, dp->lag,
+								info->addr,
+								info->vid,
+								info->db);
+			} else {
+				err = dsa_port_do_fdb_add(dp, info->addr,
+							  info->vid, info->db);
+			}
 			if (err)
 				break;
 		}
@@ -419,8 +426,15 @@  static int dsa_switch_host_fdb_del(struct dsa_switch *ds,
 
 	dsa_switch_for_each_port(dp, ds) {
 		if (dsa_port_host_address_match(dp, info->dp)) {
-			err = dsa_port_do_fdb_del(dp, info->addr, info->vid,
-						  info->db);
+			if (dsa_port_is_cpu(dp) && info->dp->cpu_port_in_lag) {
+				err = dsa_switch_do_lag_fdb_del(ds, dp->lag,
+								info->addr,
+								info->vid,
+								info->db);
+			} else {
+				err = dsa_port_do_fdb_del(dp, info->addr,
+							  info->vid, info->db);
+			}
 			if (err)
 				break;
 		}