Merge branch 'dsa-changes-for-multiple-cpu-ports-part-4'

Vladimir Oltean says:

====================
DSA changes for multiple CPU ports (part 4)

Those who have been following part 1:
https://patchwork.kernel.org/project/netdevbpf/cover/20220511095020.562461-1-vladimir.oltean@nxp.com/
part 2:
https://patchwork.kernel.org/project/netdevbpf/cover/20220521213743.2735445-1-vladimir.oltean@nxp.com/
and part 3:
https://patchwork.kernel.org/project/netdevbpf/cover/20220819174820.3585002-1-vladimir.oltean@nxp.com/
will know that I am trying to enable the second internal port pair from
the NXP LS1028A Felix switch for DSA-tagged traffic via "ocelot-8021q".

This series represents the final part of that effort. We have:

- the introduction of new UAPI in the form of IFLA_DSA_MASTER, the
  iproute2 patch for which is here:
  https://patchwork.kernel.org/project/netdevbpf/patch/20220904190025.813574-1-vladimir.oltean@nxp.com/

- preparation for LAG DSA masters in terms of suppressing some
  operations for masters in the DSA core that simply don't make sense
  when those masters are a bonding/team interface

- handling all the net device events that occur between DSA and a
  LAG DSA master, including migration to a different DSA master when the
  current master joins a LAG, or the LAG gets destroyed

- updating documentation

- adding an implementation for NXP LS1028A, where things are insanely
  complicated due to hardware limitations. We have 2 tagging protocols:

  * the native "ocelot" protocol (NPI port mode). This does not support
    CPU ports in a LAG, and supports a single DSA master. The DSA master
    can be changed between eno2 (2.5G) and eno3 (1G), but all ports must
    be down during the changing process, and user ports assigned to the
    old DSA master will refuse to come up if the user requests that
    during a "transient" state.

  * the "ocelot-8021q" software-defined protocol, where the Ethernet
    ports connected to the CPU are not actually "god mode" ports as far
    as the hardware is concerned. So here, static assignment between
    user and CPU ports is possible by editing the PGID_SRC masks for
    the port-based forwarding matrix, and "CPU ports in a LAG" simply
    means "a LAG like any other".

The series was regression-tested on LS1028A using the local_termination.sh
kselftest, in most of the possible operating modes and tagging protocols.
I have not done a detailed performance evaluation yet, but using LAG, is
possible to exceed the termination bandwidth of a single CPU port in an
iperf3 test with multiple senders and multiple receivers.

v1 at:
https://patchwork.kernel.org/project/netdevbpf/cover/20220830195932.683432-1-vladimir.oltean@nxp.com/

Previous (older) RFC at:
https://lore.kernel.org/netdev/20220523104256.3556016-1-olteanv@gmail.com/
====================

Link: https://lore.kernel.org/r/20220911010706.2137967-1-vladimir.oltean@nxp.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

4 files changed, 48 insertions, 3 deletions

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index f0068c1ff1df..9f42fc871c3b 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -253,11 +253,17 @@ struct netdev_hw_addr_list {
 #define netdev_uc_empty(dev) netdev_hw_addr_list_empty(&(dev)->uc)
 #define netdev_for_each_uc_addr(ha, dev) \
 	netdev_hw_addr_list_for_each(ha, &(dev)->uc)
+#define netdev_for_each_synced_uc_addr(_ha, _dev) \
+	netdev_for_each_uc_addr((_ha), (_dev)) \
+		if ((_ha)->sync_cnt)
 
 #define netdev_mc_count(dev) netdev_hw_addr_list_count(&(dev)->mc)
 #define netdev_mc_empty(dev) netdev_hw_addr_list_empty(&(dev)->mc)
 #define netdev_for_each_mc_addr(ha, dev) \
 	netdev_hw_addr_list_for_each(ha, &(dev)->mc)
+#define netdev_for_each_synced_mc_addr(_ha, _dev) \
+	netdev_for_each_mc_addr((_ha), (_dev)) \
+		if ((_ha)->sync_cnt)
 
 struct hh_cache {
 	unsigned int	hh_len;
diff --git a/include/net/dsa.h b/include/net/dsa.h
index f2ce12860546..d777eac5694f 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;
@@ -559,6 +562,10 @@ static inline bool dsa_is_user_port(struct dsa_switch *ds, int p)
 	list_for_each_entry((_dp), &(_dst)->ports, list) \
 		if (dsa_port_is_user((_dp)))
 
+#define dsa_tree_for_each_user_port_continue_reverse(_dp, _dst) \
+	list_for_each_entry_continue_reverse((_dp), &(_dst)->ports, list) \
+		if (dsa_port_is_user((_dp)))
+
 #define dsa_tree_for_each_cpu_port(_dp, _dst) \
 	list_for_each_entry((_dp), &(_dst)->ports, list) \
 		if (dsa_port_is_cpu((_dp)))
@@ -718,6 +725,14 @@ static inline bool dsa_port_offloads_lag(struct dsa_port *dp,
 	return dsa_port_lag_dev_get(dp) == lag->dev;
 }
 
+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;
+}
+
 static inline
 struct net_device *dsa_port_to_bridge_port(const struct dsa_port *dp)
 {
@@ -802,6 +817,12 @@ dsa_tree_offloads_bridge_dev(struct dsa_switch_tree *dst,
 	return false;
 }
 
+static inline bool dsa_port_tree_same(const struct dsa_port *a,
+				      const struct dsa_port *b)
+{
+	return a->ds->dst == b->ds->dst;
+}
+
 typedef int dsa_fdb_dump_cb_t(const unsigned char *addr, u16 vid,
 			      bool is_static, void *data);
 struct dsa_switch_ops {
@@ -825,6 +846,10 @@ struct dsa_switch_ops {
 	int	(*connect_tag_protocol)(struct dsa_switch *ds,
 					enum dsa_tag_protocol proto);
 
+	int	(*port_change_master)(struct dsa_switch *ds, int port,
+				      struct net_device *master,
+				      struct netlink_ext_ack *extack);
+
 	/* Optional switch-wide initialization and destruction methods */
 	int	(*setup)(struct dsa_switch *ds);
 	void	(*teardown)(struct dsa_switch *ds);
@@ -1081,7 +1106,8 @@ struct dsa_switch_ops {
 					int port);
 	int	(*crosschip_lag_join)(struct dsa_switch *ds, int sw_index,
 				      int port, struct dsa_lag lag,
-				      struct netdev_lag_upper_info *info);
+				      struct netdev_lag_upper_info *info,
+				      struct netlink_ext_ack *extack);
 	int	(*crosschip_lag_leave)(struct dsa_switch *ds, int sw_index,
 				       int port, struct dsa_lag lag);
 
@@ -1156,7 +1182,8 @@ 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 dsa_lag lag,
-				 struct netdev_lag_upper_info *info);
+				 struct netdev_lag_upper_info *info,
+				 struct netlink_ext_ack *extack);
 	int	(*port_lag_leave)(struct dsa_switch *ds, int port,
 				  struct dsa_lag lag);
 
diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h
index 355cfdedc43b..967ba30ea636 100644
--- a/include/soc/mscc/ocelot.h
+++ b/include/soc/mscc/ocelot.h
@@ -1229,10 +1229,12 @@ int ocelot_port_mdb_del(struct ocelot *ocelot, int port,
 			const struct net_device *bridge);
 int ocelot_port_lag_join(struct ocelot *ocelot, int port,
 			 struct net_device *bond,
-			 struct netdev_lag_upper_info *info);
+			 struct netdev_lag_upper_info *info,
+			 struct netlink_ext_ack *extack);
 void ocelot_port_lag_leave(struct ocelot *ocelot, int port,
 			   struct net_device *bond);
 void ocelot_port_lag_change(struct ocelot *ocelot, int port, bool lag_tx_active);
+int ocelot_bond_get_id(struct ocelot *ocelot, struct net_device *bond);
 
 int ocelot_devlink_sb_register(struct ocelot *ocelot);
 void ocelot_devlink_sb_unregister(struct ocelot *ocelot);
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 0bfa9a99ebb6..3d39fb398d65 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -1375,4 +1375,14 @@ enum {
 
 #define IFLA_MCTP_MAX (__IFLA_MCTP_MAX - 1)
 
+/* DSA section */
+
+enum {
+	IFLA_DSA_UNSPEC,
+	IFLA_DSA_MASTER,
+	__IFLA_DSA_MAX,
+};
+
+#define IFLA_DSA_MAX	(__IFLA_DSA_MAX - 1)
+
 #endif /* _UAPI_LINUX_IF_LINK_H */