Merge branch 'offload-software-learnt-bridge-addresses-to-dsa'

Vladimir Oltean says:

====================
Offload software learnt bridge addresses to DSA

This series tries to make DSA behave a bit more sanely when bridged with
"foreign" (non-DSA) interfaces and source address learning is not
supported on the hardware CPU port (which would make things work more
seamlessly without software intervention). When a station A connected to
a DSA switch port needs to talk to another station B connected to a
non-DSA port through the Linux bridge, DSA must explicitly add a route
for station B towards its CPU port.

Initial RFC was posted here:
https://patchwork.ozlabs.org/project/netdev/cover/20201108131953.2462644-1-olteanv@gmail.com/

v2 was posted here:
https://patchwork.kernel.org/project/netdevbpf/cover/20201213024018.772586-1-vladimir.oltean@nxp.com/

v3 was posted here:
https://patchwork.kernel.org/project/netdevbpf/cover/20201213140710.1198050-1-vladimir.oltean@nxp.com/

This is a resend of the previous v3 with some added Reviewed-by tags.
====================

Link: https://lore.kernel.org/r/20210106095136.224739-1-olteanv@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

5 files changed, 130 insertions, 63 deletions

diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c
index 7dc230677b78..90c3c76f21b2 100644
--- a/drivers/net/dsa/ocelot/felix.c
+++ b/drivers/net/dsa/ocelot/felix.c
@@ -629,6 +629,7 @@ static int felix_setup(struct dsa_switch *ds)
 
 	ds->mtu_enforcement_ingress = true;
 	ds->configure_vlan_while_not_filtering = true;
+	ds->assisted_learning_on_cpu_port = true;
 
 	return 0;
 }
diff --git a/include/net/dsa.h b/include/net/dsa.h
index 4e60d2610f20..6b74690bd8d4 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -319,6 +319,11 @@ struct dsa_switch {
 	 */
 	bool			untag_bridge_pvid;
 
+	/* Let DSA manage the FDB entries towards the CPU, based on the
+	 * software bridge database.
+	 */
+	bool			assisted_learning_on_cpu_port;
+
 	/* In case vlan_filtering_is_global is set, the VLAN awareness state
 	 * should be retrieved from here and not from the per-port settings.
 	 */
diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
index 32ac8343b0ba..b7490237f3fc 100644
--- a/net/bridge/br_fdb.c
+++ b/net/bridge/br_fdb.c
@@ -602,6 +602,7 @@ void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source,
 			/* fastpath: update of existing entry */
 			if (unlikely(source != fdb->dst &&
 				     !test_bit(BR_FDB_STICKY, &fdb->flags))) {
+				br_switchdev_fdb_notify(fdb, RTM_DELNEIGH);
 				fdb->dst = source;
 				fdb_modified = true;
 				/* Take over HW learned entry */
diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h
index 7c96aae9062c..c04225f74929 100644
--- a/net/dsa/dsa_priv.h
+++ b/net/dsa/dsa_priv.h
@@ -73,6 +73,18 @@ struct dsa_notifier_mtu_info {
 	int mtu;
 };
 
+struct dsa_switchdev_event_work {
+	struct dsa_switch *ds;
+	int port;
+	struct work_struct work;
+	unsigned long event;
+	/* Specific for SWITCHDEV_FDB_ADD_TO_DEVICE and
+	 * SWITCHDEV_FDB_DEL_TO_DEVICE
+	 */
+	unsigned char addr[ETH_ALEN];
+	u16 vid;
+};
+
 struct dsa_slave_priv {
 	/* Copy of CPU port xmit for faster access in slave transmit hot path */
 	struct sk_buff *	(*xmit)(struct sk_buff *skb,
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 4a0498bf6c65..456576f75a50 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -2047,119 +2047,167 @@ static int dsa_slave_netdevice_event(struct notifier_block *nb,
 	return NOTIFY_DONE;
 }
 
-struct dsa_switchdev_event_work {
-	struct work_struct work;
-	struct switchdev_notifier_fdb_info fdb_info;
-	struct net_device *dev;
-	unsigned long event;
-};
+static void
+dsa_fdb_offload_notify(struct dsa_switchdev_event_work *switchdev_work)
+{
+	struct dsa_switch *ds = switchdev_work->ds;
+	struct switchdev_notifier_fdb_info info;
+	struct dsa_port *dp;
+
+	if (!dsa_is_user_port(ds, switchdev_work->port))
+		return;
+
+	info.addr = switchdev_work->addr;
+	info.vid = switchdev_work->vid;
+	info.offloaded = true;
+	dp = dsa_to_port(ds, switchdev_work->port);
+	call_switchdev_notifiers(SWITCHDEV_FDB_OFFLOADED,
+				 dp->slave, &info.info, NULL);
+}
 
 static void dsa_slave_switchdev_event_work(struct work_struct *work)
 {
 	struct dsa_switchdev_event_work *switchdev_work =
 		container_of(work, struct dsa_switchdev_event_work, work);
-	struct net_device *dev = switchdev_work->dev;
-	struct switchdev_notifier_fdb_info *fdb_info;
-	struct dsa_port *dp = dsa_slave_to_port(dev);
+	struct dsa_switch *ds = switchdev_work->ds;
+	struct dsa_port *dp;
 	int err;
 
+	dp = dsa_to_port(ds, switchdev_work->port);
+
 	rtnl_lock();
 	switch (switchdev_work->event) {
 	case SWITCHDEV_FDB_ADD_TO_DEVICE:
-		fdb_info = &switchdev_work->fdb_info;
-		if (!fdb_info->added_by_user)
-			break;
-
-		err = dsa_port_fdb_add(dp, fdb_info->addr, fdb_info->vid);
+		err = dsa_port_fdb_add(dp, switchdev_work->addr,
+				       switchdev_work->vid);
 		if (err) {
-			netdev_dbg(dev, "fdb add failed err=%d\n", err);
+			dev_err(ds->dev,
+				"port %d failed to add %pM vid %d to fdb: %d\n",
+				dp->index, switchdev_work->addr,
+				switchdev_work->vid, err);
 			break;
 		}
-		fdb_info->offloaded = true;
-		call_switchdev_notifiers(SWITCHDEV_FDB_OFFLOADED, dev,
-					 &fdb_info->info, NULL);
+		dsa_fdb_offload_notify(switchdev_work);
 		break;
 
 	case SWITCHDEV_FDB_DEL_TO_DEVICE:
-		fdb_info = &switchdev_work->fdb_info;
-		if (!fdb_info->added_by_user)
-			break;
-
-		err = dsa_port_fdb_del(dp, fdb_info->addr, fdb_info->vid);
+		err = dsa_port_fdb_del(dp, switchdev_work->addr,
+				       switchdev_work->vid);
 		if (err) {
-			netdev_dbg(dev, "fdb del failed err=%d\n", err);
-			dev_close(dev);
+			dev_err(ds->dev,
+				"port %d failed to delete %pM vid %d from fdb: %d\n",
+				dp->index, switchdev_work->addr,
+				switchdev_work->vid, err);
 		}
+
 		break;
 	}
 	rtnl_unlock();
 
-	kfree(switchdev_work->fdb_info.addr);
 	kfree(switchdev_work);
-	dev_put(dev);
+	if (dsa_is_user_port(ds, dp->index))
+		dev_put(dp->slave);
 }
 
-static int
-dsa_slave_switchdev_fdb_work_init(struct dsa_switchdev_event_work *
-				  switchdev_work,
-				  const struct switchdev_notifier_fdb_info *
-				  fdb_info)
-{
-	memcpy(&switchdev_work->fdb_info, fdb_info,
-	       sizeof(switchdev_work->fdb_info));
-	switchdev_work->fdb_info.addr = kzalloc(ETH_ALEN, GFP_ATOMIC);
-	if (!switchdev_work->fdb_info.addr)
-		return -ENOMEM;
-	ether_addr_copy((u8 *)switchdev_work->fdb_info.addr,
-			fdb_info->addr);
+static int dsa_lower_dev_walk(struct net_device *lower_dev,
+			      struct netdev_nested_priv *priv)
+{
+	if (dsa_slave_dev_check(lower_dev)) {
+		priv->data = (void *)netdev_priv(lower_dev);
+		return 1;
+	}
+
 	return 0;
 }
 
+static struct dsa_slave_priv *dsa_slave_dev_lower_find(struct net_device *dev)
+{
+	struct netdev_nested_priv priv = {
+		.data = NULL,
+	};
+
+	netdev_walk_all_lower_dev_rcu(dev, dsa_lower_dev_walk, &priv);
+
+	return (struct dsa_slave_priv *)priv.data;
+}
+
 /* Called under rcu_read_lock() */
 static int dsa_slave_switchdev_event(struct notifier_block *unused,
 				     unsigned long event, void *ptr)
 {
 	struct net_device *dev = switchdev_notifier_info_to_dev(ptr);
+	const struct switchdev_notifier_fdb_info *fdb_info;
 	struct dsa_switchdev_event_work *switchdev_work;
+	struct dsa_port *dp;
 	int err;
 
-	if (event == SWITCHDEV_PORT_ATTR_SET) {
+	switch (event) {
+	case SWITCHDEV_PORT_ATTR_SET:
 		err = switchdev_handle_port_attr_set(dev, ptr,
 						     dsa_slave_dev_check,
 						     dsa_slave_port_attr_set);
 		return notifier_from_errno(err);
-	}
+	case SWITCHDEV_FDB_ADD_TO_DEVICE:
+	case SWITCHDEV_FDB_DEL_TO_DEVICE:
+		fdb_info = ptr;
 
-	if (!dsa_slave_dev_check(dev))
-		return NOTIFY_DONE;
+		if (dsa_slave_dev_check(dev)) {
+			if (!fdb_info->added_by_user)
+				return NOTIFY_OK;
 
-	switchdev_work = kzalloc(sizeof(*switchdev_work), GFP_ATOMIC);
-	if (!switchdev_work)
-		return NOTIFY_BAD;
+			dp = dsa_slave_to_port(dev);
+		} else {
+			/* Snoop addresses learnt on foreign interfaces
+			 * bridged with us, for switches that don't
+			 * automatically learn SA from CPU-injected traffic
+			 */
+			struct net_device *br_dev;
+			struct dsa_slave_priv *p;
 
-	INIT_WORK(&switchdev_work->work,
-		  dsa_slave_switchdev_event_work);
-	switchdev_work->dev = dev;
-	switchdev_work->event = event;
+			br_dev = netdev_master_upper_dev_get_rcu(dev);
+			if (!br_dev)
+				return NOTIFY_DONE;
 
-	switch (event) {
-	case SWITCHDEV_FDB_ADD_TO_DEVICE:
-	case SWITCHDEV_FDB_DEL_TO_DEVICE:
-		if (dsa_slave_switchdev_fdb_work_init(switchdev_work, ptr))
-			goto err_fdb_work_init;
-		dev_hold(dev);
+			if (!netif_is_bridge_master(br_dev))
+				return NOTIFY_DONE;
+
+			p = dsa_slave_dev_lower_find(br_dev);
+			if (!p)
+				return NOTIFY_DONE;
+
+			dp = p->dp->cpu_dp;
+
+			if (!dp->ds->assisted_learning_on_cpu_port)
+				return NOTIFY_DONE;
+		}
+
+		if (!dp->ds->ops->port_fdb_add || !dp->ds->ops->port_fdb_del)
+			return NOTIFY_DONE;
+
+		switchdev_work = kzalloc(sizeof(*switchdev_work), GFP_ATOMIC);
+		if (!switchdev_work)
+			return NOTIFY_BAD;
+
+		INIT_WORK(&switchdev_work->work,
+			  dsa_slave_switchdev_event_work);
+		switchdev_work->ds = dp->ds;
+		switchdev_work->port = dp->index;
+		switchdev_work->event = event;
+
+		ether_addr_copy(switchdev_work->addr,
+				fdb_info->addr);
+		switchdev_work->vid = fdb_info->vid;
+
+		/* Hold a reference on the slave for dsa_fdb_offload_notify */
+		if (dsa_is_user_port(dp->ds, dp->index))
+			dev_hold(dev);
+		dsa_schedule_work(&switchdev_work->work);
 		break;
 	default:
-		kfree(switchdev_work);
 		return NOTIFY_DONE;
 	}
 
-	dsa_schedule_work(&switchdev_work->work);
 	return NOTIFY_OK;
-
-err_fdb_work_init:
-	kfree(switchdev_work);
-	return NOTIFY_BAD;
 }
 
 static int dsa_slave_switchdev_blocking_event(struct notifier_block *unused,