Merge branch 'fdb-entries-on-dsa-lag-interfaces'

Vladimir Oltean says:

====================
FDB entries on DSA LAG interfaces

This work permits having static and local FDB entries on LAG interfaces
that are offloaded by DSA ports. New API needs to be introduced in
drivers. To maintain consistency with the bridging offload code, I've
taken the liberty to reorganize the data structures added by Tobias in
the DSA core a little bit.

Tested on NXP LS1028A (felix switch). Would appreciate feedback/testing
on other platforms too. Testing procedure was the one described here:
https://patchwork.kernel.org/project/netdevbpf/cover/20210205130240.4072854-1-vladimir.oltean@nxp.com/

with this script:

ip link del bond0
ip link add bond0 type bond mode 802.3ad
ip link set swp1 down && ip link set swp1 master bond0 && ip link set swp1 up
ip link set swp2 down && ip link set swp2 master bond0 && ip link set swp2 up
ip link del br0
ip link add br0 type bridge && ip link set br0 up
ip link set br0 arp off
ip link set bond0 master br0 && ip link set bond0 up
ip link set swp0 master br0 && ip link set swp0 up
ip link set dev bond0 type bridge_slave flood off learning off
bridge fdb add dev bond0 <mac address of other eno0> master static

I'm noticing a problem in 'bridge fdb dump' with the 'self' entries, and
I didn't solve this. On Ocelot, an entry learned on a LAG is reported as
being on the first member port of it (so instead of saying 'self bond0',
it says 'self swp1'). This is better than not seeing the entry at all,
but when DSA queries for the FDBs on a port via ds->ops->port_fdb_dump,
it never queries for FDBs on a LAG. Not clear what we should do there,
we aren't in control of the ->ndo_fdb_dump of the bonding/team drivers.
Alternatively, we could just consider the 'self' entries reported via
ndo_fdb_dump as "better than nothing", and concentrate on the 'master'
entries that are in sync with the bridge when packets are flooded to
software.
====================

Link: https://lore.kernel.org/r/20220223140054.3379617-1-vladimir.oltean@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

3 files changed, 63 insertions, 25 deletions

diff --git a/include/net/dsa.h b/include/net/dsa.h
index f13de2d8aef3..01faba89c987 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -116,6 +116,14 @@ struct dsa_netdevice_ops {
 #define MODULE_ALIAS_DSA_TAG_DRIVER(__proto)				\
 	MODULE_ALIAS(DSA_TAG_DRIVER_ALIAS __stringify(__proto##_VALUE))
 
+struct dsa_lag {
+	struct net_device *dev;
+	unsigned int id;
+	struct mutex fdb_lock;
+	struct list_head fdbs;
+	refcount_t refcount;
+};
+
 struct dsa_switch_tree {
 	struct list_head	list;
 
@@ -134,7 +142,7 @@ struct dsa_switch_tree {
 	/* Maps offloaded LAG netdevs to a zero-based linear ID for
 	 * drivers that need it.
 	 */
-	struct net_device **lags;
+	struct dsa_lag **lags;
 
 	/* Tagging protocol operations */
 	const struct dsa_device_ops *tag_ops;
@@ -163,32 +171,36 @@ struct dsa_switch_tree {
 	unsigned int last_switch;
 };
 
+/* LAG IDs are one-based, the dst->lags array is zero-based */
 #define dsa_lags_foreach_id(_id, _dst)				\
-	for ((_id) = 0; (_id) < (_dst)->lags_len; (_id)++)	\
-		if ((_dst)->lags[(_id)])
+	for ((_id) = 1; (_id) <= (_dst)->lags_len; (_id)++)	\
+		if ((_dst)->lags[(_id) - 1])
 
 #define dsa_lag_foreach_port(_dp, _dst, _lag)			\
 	list_for_each_entry((_dp), &(_dst)->ports, list)	\
-		if ((_dp)->lag_dev == (_lag))
+		if (dsa_port_offloads_lag((_dp), (_lag)))
 
 #define dsa_hsr_foreach_port(_dp, _ds, _hsr)			\
 	list_for_each_entry((_dp), &(_ds)->dst->ports, list)	\
 		if ((_dp)->ds == (_ds) && (_dp)->hsr_dev == (_hsr))
 
-static inline struct net_device *dsa_lag_dev(struct dsa_switch_tree *dst,
-					     unsigned int id)
+static inline struct dsa_lag *dsa_lag_by_id(struct dsa_switch_tree *dst,
+					    unsigned int id)
 {
-	return dst->lags[id];
+	/* DSA LAG IDs are one-based, dst->lags is zero-based */
+	return dst->lags[id - 1];
 }
 
 static inline int dsa_lag_id(struct dsa_switch_tree *dst,
-			     struct net_device *lag)
+			     struct net_device *lag_dev)
 {
 	unsigned int id;
 
 	dsa_lags_foreach_id(id, dst) {
-		if (dsa_lag_dev(dst, id) == lag)
-			return id;
+		struct dsa_lag *lag = dsa_lag_by_id(dst, id);
+
+		if (lag->dev == lag_dev)
+			return lag->id;
 	}
 
 	return -ENODEV;
@@ -291,7 +303,7 @@ struct dsa_port {
 	struct devlink_port	devlink_port;
 	struct phylink		*pl;
 	struct phylink_config	pl_config;
-	struct net_device	*lag_dev;
+	struct dsa_lag		*lag;
 	struct net_device	*hsr_dev;
 
 	struct list_head list;
@@ -641,14 +653,30 @@ static inline bool dsa_port_is_vlan_filtering(const struct dsa_port *dp)
 		return dp->vlan_filtering;
 }
 
+static inline unsigned int dsa_port_lag_id_get(struct dsa_port *dp)
+{
+	return dp->lag ? dp->lag->id : 0;
+}
+
+static inline struct net_device *dsa_port_lag_dev_get(struct dsa_port *dp)
+{
+	return dp->lag ? dp->lag->dev : NULL;
+}
+
+static inline bool dsa_port_offloads_lag(struct dsa_port *dp,
+					 const struct dsa_lag *lag)
+{
+	return dsa_port_lag_dev_get(dp) == lag->dev;
+}
+
 static inline
 struct net_device *dsa_port_to_bridge_port(const struct dsa_port *dp)
 {
 	if (!dp->bridge)
 		return NULL;
 
-	if (dp->lag_dev)
-		return dp->lag_dev;
+	if (dp->lag)
+		return dp->lag->dev;
 	else if (dp->hsr_dev)
 		return dp->hsr_dev;
 
@@ -918,6 +946,10 @@ struct dsa_switch_ops {
 				const unsigned char *addr, u16 vid);
 	int	(*port_fdb_dump)(struct dsa_switch *ds, int port,
 				 dsa_fdb_dump_cb_t *cb, void *data);
+	int	(*lag_fdb_add)(struct dsa_switch *ds, struct dsa_lag lag,
+			       const unsigned char *addr, u16 vid);
+	int	(*lag_fdb_del)(struct dsa_switch *ds, struct dsa_lag lag,
+			       const unsigned char *addr, u16 vid);
 
 	/*
 	 * Multicast database
@@ -966,10 +998,10 @@ struct dsa_switch_ops {
 	int	(*crosschip_lag_change)(struct dsa_switch *ds, int sw_index,
 					int port);
 	int	(*crosschip_lag_join)(struct dsa_switch *ds, int sw_index,
-				      int port, struct net_device *lag,
+				      int port, struct dsa_lag lag,
 				      struct netdev_lag_upper_info *info);
 	int	(*crosschip_lag_leave)(struct dsa_switch *ds, int sw_index,
-				       int port, struct net_device *lag);
+				       int port, struct dsa_lag lag);
 
 	/*
 	 * PTP functionality
@@ -1041,10 +1073,10 @@ struct dsa_switch_ops {
 	 */
 	int	(*port_lag_change)(struct dsa_switch *ds, int port);
 	int	(*port_lag_join)(struct dsa_switch *ds, int port,
-				 struct net_device *lag,
+				 struct dsa_lag lag,
 				 struct netdev_lag_upper_info *info);
 	int	(*port_lag_leave)(struct dsa_switch *ds, int port,
-				  struct net_device *lag);
+				  struct dsa_lag lag);
 
 	/*
 	 * HSR integration
diff --git a/include/net/switchdev.h b/include/net/switchdev.h
index c32e1c8f79ec..3e424d40fae3 100644
--- a/include/net/switchdev.h
+++ b/include/net/switchdev.h
@@ -313,10 +313,7 @@ int switchdev_handle_fdb_event_to_device(struct net_device *dev, unsigned long e
 					     const struct net_device *foreign_dev),
 		int (*mod_cb)(struct net_device *dev, struct net_device *orig_dev,
 			      unsigned long event, const void *ctx,
-			      const struct switchdev_notifier_fdb_info *fdb_info),
-		int (*lag_mod_cb)(struct net_device *dev, struct net_device *orig_dev,
-				  unsigned long event, const void *ctx,
-				  const struct switchdev_notifier_fdb_info *fdb_info));
+			      const struct switchdev_notifier_fdb_info *fdb_info));
 
 int switchdev_handle_port_obj_add(struct net_device *dev,
 			struct switchdev_notifier_port_obj_info *port_obj_info,
@@ -443,10 +440,7 @@ switchdev_handle_fdb_event_to_device(struct net_device *dev, unsigned long event
 					     const struct net_device *foreign_dev),
 		int (*mod_cb)(struct net_device *dev, struct net_device *orig_dev,
 			      unsigned long event, const void *ctx,
-			      const struct switchdev_notifier_fdb_info *fdb_info),
-		int (*lag_mod_cb)(struct net_device *dev, struct net_device *orig_dev,
-				  unsigned long event, const void *ctx,
-				  const struct switchdev_notifier_fdb_info *fdb_info))
+			      const struct switchdev_notifier_fdb_info *fdb_info))
 {
 	return 0;
 }
diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h
index 78f56502bc09..dd4fc34d2992 100644
--- a/include/soc/mscc/ocelot.h
+++ b/include/soc/mscc/ocelot.h
@@ -635,6 +635,13 @@ enum macaccess_entry_type {
 #define OCELOT_QUIRK_PCS_PERFORMS_RATE_ADAPTATION	BIT(0)
 #define OCELOT_QUIRK_QSGMII_PORTS_MUST_BE_UP		BIT(1)
 
+struct ocelot_lag_fdb {
+	unsigned char addr[ETH_ALEN];
+	u16 vid;
+	struct net_device *bond;
+	struct list_head list;
+};
+
 struct ocelot_port {
 	struct ocelot			*ocelot;
 
@@ -690,6 +697,7 @@ struct ocelot {
 
 	struct list_head		vlans;
 	struct list_head		traps;
+	struct list_head		lag_fdbs;
 
 	/* Switches like VSC9959 have flooding per traffic class */
 	int				num_flooding_pgids;
@@ -866,6 +874,10 @@ int ocelot_fdb_add(struct ocelot *ocelot, int port,
 		   const unsigned char *addr, u16 vid);
 int ocelot_fdb_del(struct ocelot *ocelot, int port,
 		   const unsigned char *addr, u16 vid);
+int ocelot_lag_fdb_add(struct ocelot *ocelot, struct net_device *bond,
+		       const unsigned char *addr, u16 vid);
+int ocelot_lag_fdb_del(struct ocelot *ocelot, struct net_device *bond,
+		       const unsigned char *addr, u16 vid);
 int ocelot_vlan_prepare(struct ocelot *ocelot, int port, u16 vid, bool pvid,
 			bool untagged, struct netlink_ext_ack *extack);
 int ocelot_vlan_add(struct ocelot *ocelot, int port, u16 vid, bool pvid,