Merge branch 'net-bridge-multiple-spanning-trees'

Tobias Waldekranz says:

====================
net: bridge: Multiple Spanning Trees

The bridge has had per-VLAN STP support for a while now, since:

https://lore.kernel.org/netdev/20200124114022.10883-1-nikolay@cumulusnetworks.com/

The current implementation has some problems:

- The mapping from VLAN to STP state is fixed as 1:1, i.e. each VLAN
  is managed independently. This is awkward from an MSTP (802.1Q-2018,
  Clause 13.5) point of view, where the model is that multiple VLANs
  are grouped into MST instances.

  Because of the way that the standard is written, presumably, this is
  also reflected in hardware implementations. It is not uncommon for a
  switch to support the full 4k range of VIDs, but that the pool of
  MST instances is much smaller. Some examples:

  Marvell LinkStreet (mv88e6xxx): 4k VLANs, but only 64 MSTIs
  Marvell Prestera: 4k VLANs, but only 128 MSTIs
  Microchip SparX-5i: 4k VLANs, but only 128 MSTIs

- By default, the feature is enabled, and there is no way to disable
  it. This makes it hard to add offloading in a backwards compatible
  way, since any underlying switchdevs have no way to refuse the
  function if the hardware does not support it

- The port-global STP state has precedence over per-VLAN states. In
  MSTP, as far as I understand it, all VLANs will use the common
  spanning tree (CST) by default - through traffic engineering you can
  then optimize your network to group subsets of VLANs to use
  different trees (MSTI). To my understanding, the way this is
  typically managed in silicon is roughly:

  Incoming packet:
  .----.----.--------------.----.-------------
  | DA | SA | 802.1Q VID=X | ET | Payload ...
  '----'----'--------------'----'-------------
                        |
                        '->|\     .----------------------------.
                           | +--> | VID | Members | ... | MSTI |
                   PVID -->|/     |-----|---------|-----|------|
                                  |   1 | 0001001 | ... |    0 |
                                  |   2 | 0001010 | ... |   10 |
                                  |   3 | 0001100 | ... |   10 |
                                  '----------------------------'
                                                             |
                               .-----------------------------'
                               |  .------------------------.
                               '->| MSTI | Fwding | Lrning |
                                  |------|--------|--------|
                                  |    0 | 111110 | 111110 |
                                  |   10 | 110111 | 110111 |
                                  '------------------------'

  What this is trying to show is that the STP state (whether MSTP is
  used, or ye olde STP) is always accessed via the VLAN table. If STP
  is running, all MSTI pointers in that table will reference the same
  index in the STP stable - if MSTP is running, some VLANs may point
  to other trees (like in this example).

  The fact that in the Linux bridge, the global state (think: index 0
  in most hardware implementations) is supposed to override the
  per-VLAN state, is very awkward to offload. In effect, this means
  that when the global state changes to blocking, drivers will have to
  iterate over all MSTIs in use, and alter them all to match. This
  also means that you have to cache whether the hardware state is
  currently tracking the global state or the per-VLAN state. In the
  first case, you also have to cache the per-VLAN state so that you
  can restore it if the global state transitions back to forwarding.

This series adds a new mst_enable bridge setting (as suggested by Nik)
that can only be changed when no VLANs are configured on the
bridge. Enabling this mode has the following effect:

- The port-global STP state is used to represent the CST (Common
  Spanning Tree) (1/15)

- Ingress STP filtering is deferred until the frame's VLAN has been
  resolved (1/15)

- The preexisting per-VLAN states can no longer be controlled directly
  (1/15). They are instead placed under the MST module's control,
  which is managed using a new netlink interface (described in 3/15)

- VLANs can br mapped to MSTIs in an arbitrary M:N fashion, using a
  new global VLAN option (2/15)

Switchdev notifications are added so that a driver can track:
- MST enabled state
- VID to MSTI mappings
- MST port states

An offloading implementation is this provided for mv88e6xxx.
====================

Link: https://lore.kernel.org/r/20220316150857.2442916-1-tobias@waldekranz.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

5 files changed, 60 insertions, 0 deletions

diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h
index 3aae023a9353..d62ef428e3aa 100644
--- a/include/linux/if_bridge.h
+++ b/include/linux/if_bridge.h
@@ -119,6 +119,9 @@ int br_vlan_get_info(const struct net_device *dev, u16 vid,
 		     struct bridge_vlan_info *p_vinfo);
 int br_vlan_get_info_rcu(const struct net_device *dev, u16 vid,
 			 struct bridge_vlan_info *p_vinfo);
+bool br_mst_enabled(const struct net_device *dev);
+int br_mst_get_info(const struct net_device *dev, u16 msti, unsigned long *vids);
+int br_mst_get_state(const struct net_device *dev, u16 msti, u8 *state);
 #else
 static inline bool br_vlan_enabled(const struct net_device *dev)
 {
@@ -151,6 +154,22 @@ static inline int br_vlan_get_info_rcu(const struct net_device *dev, u16 vid,
 {
 	return -EINVAL;
 }
+
+static inline bool br_mst_enabled(const struct net_device *dev)
+{
+	return false;
+}
+
+static inline int br_mst_get_info(const struct net_device *dev, u16 msti,
+				  unsigned long *vids)
+{
+	return -EINVAL;
+}
+static inline int br_mst_get_state(const struct net_device *dev, u16 msti,
+				   u8 *state)
+{
+	return -EINVAL;
+}
 #endif
 
 #if IS_ENABLED(CONFIG_BRIDGE)
diff --git a/include/net/dsa.h b/include/net/dsa.h
index 9bfe984fcdbf..06cdefd3b9dd 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -957,7 +957,10 @@ struct dsa_switch_ops {
 				     struct dsa_bridge bridge);
 	void	(*port_stp_state_set)(struct dsa_switch *ds, int port,
 				      u8 state);
+	int	(*port_mst_state_set)(struct dsa_switch *ds, int port,
+				      const struct switchdev_mst_state *state);
 	void	(*port_fast_age)(struct dsa_switch *ds, int port);
+	int	(*port_vlan_fast_age)(struct dsa_switch *ds, int port, u16 vid);
 	int	(*port_pre_bridge_flags)(struct dsa_switch *ds, int port,
 					 struct switchdev_brport_flags flags,
 					 struct netlink_ext_ack *extack);
@@ -976,6 +979,9 @@ struct dsa_switch_ops {
 				 struct netlink_ext_ack *extack);
 	int	(*port_vlan_del)(struct dsa_switch *ds, int port,
 				 const struct switchdev_obj_port_vlan *vlan);
+	int	(*vlan_msti_set)(struct dsa_switch *ds, struct dsa_bridge bridge,
+				 const struct switchdev_vlan_msti *msti);
+
 	/*
 	 * Forwarding database
 	 */
diff --git a/include/net/switchdev.h b/include/net/switchdev.h
index 3e424d40fae3..aa0171d5786d 100644
--- a/include/net/switchdev.h
+++ b/include/net/switchdev.h
@@ -19,6 +19,7 @@
 enum switchdev_attr_id {
 	SWITCHDEV_ATTR_ID_UNDEFINED,
 	SWITCHDEV_ATTR_ID_PORT_STP_STATE,
+	SWITCHDEV_ATTR_ID_PORT_MST_STATE,
 	SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS,
 	SWITCHDEV_ATTR_ID_PORT_PRE_BRIDGE_FLAGS,
 	SWITCHDEV_ATTR_ID_PORT_MROUTER,
@@ -27,7 +28,14 @@ enum switchdev_attr_id {
 	SWITCHDEV_ATTR_ID_BRIDGE_VLAN_PROTOCOL,
 	SWITCHDEV_ATTR_ID_BRIDGE_MC_DISABLED,
 	SWITCHDEV_ATTR_ID_BRIDGE_MROUTER,
+	SWITCHDEV_ATTR_ID_BRIDGE_MST,
 	SWITCHDEV_ATTR_ID_MRP_PORT_ROLE,
+	SWITCHDEV_ATTR_ID_VLAN_MSTI,
+};
+
+struct switchdev_mst_state {
+	u16 msti;
+	u8 state;
 };
 
 struct switchdev_brport_flags {
@@ -35,6 +43,11 @@ struct switchdev_brport_flags {
 	unsigned long mask;
 };
 
+struct switchdev_vlan_msti {
+	u16 vid;
+	u16 msti;
+};
+
 struct switchdev_attr {
 	struct net_device *orig_dev;
 	enum switchdev_attr_id id;
@@ -43,13 +56,16 @@ struct switchdev_attr {
 	void (*complete)(struct net_device *dev, int err, void *priv);
 	union {
 		u8 stp_state;				/* PORT_STP_STATE */
+		struct switchdev_mst_state mst_state;	/* PORT_MST_STATE */
 		struct switchdev_brport_flags brport_flags; /* PORT_BRIDGE_FLAGS */
 		bool mrouter;				/* PORT_MROUTER */
 		clock_t ageing_time;			/* BRIDGE_AGEING_TIME */
 		bool vlan_filtering;			/* BRIDGE_VLAN_FILTERING */
 		u16 vlan_protocol;			/* BRIDGE_VLAN_PROTOCOL */
+		bool mst;				/* BRIDGE_MST */
 		bool mc_disabled;			/* MC_DISABLED */
 		u8 mrp_port_role;			/* MRP_PORT_ROLE */
+		struct switchdev_vlan_msti vlan_msti;	/* VLAN_MSTI */
 	} u;
 };
 
diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h
index 2711c3522010..a86a7e7b811f 100644
--- a/include/uapi/linux/if_bridge.h
+++ b/include/uapi/linux/if_bridge.h
@@ -122,6 +122,7 @@ enum {
 	IFLA_BRIDGE_VLAN_TUNNEL_INFO,
 	IFLA_BRIDGE_MRP,
 	IFLA_BRIDGE_CFM,
+	IFLA_BRIDGE_MST,
 	__IFLA_BRIDGE_MAX,
 };
 #define IFLA_BRIDGE_MAX (__IFLA_BRIDGE_MAX - 1)
@@ -453,6 +454,21 @@ enum {
 
 #define IFLA_BRIDGE_CFM_CC_PEER_STATUS_MAX (__IFLA_BRIDGE_CFM_CC_PEER_STATUS_MAX - 1)
 
+enum {
+	IFLA_BRIDGE_MST_UNSPEC,
+	IFLA_BRIDGE_MST_ENTRY,
+	__IFLA_BRIDGE_MST_MAX,
+};
+#define IFLA_BRIDGE_MST_MAX (__IFLA_BRIDGE_MST_MAX - 1)
+
+enum {
+	IFLA_BRIDGE_MST_ENTRY_UNSPEC,
+	IFLA_BRIDGE_MST_ENTRY_MSTI,
+	IFLA_BRIDGE_MST_ENTRY_STATE,
+	__IFLA_BRIDGE_MST_ENTRY_MAX,
+};
+#define IFLA_BRIDGE_MST_ENTRY_MAX (__IFLA_BRIDGE_MST_ENTRY_MAX - 1)
+
 struct bridge_stp_xstats {
 	__u64 transition_blk;
 	__u64 transition_fwd;
@@ -564,6 +580,7 @@ enum {
 	BRIDGE_VLANDB_GOPTS_MCAST_QUERIER,
 	BRIDGE_VLANDB_GOPTS_MCAST_ROUTER_PORTS,
 	BRIDGE_VLANDB_GOPTS_MCAST_QUERIER_STATE,
+	BRIDGE_VLANDB_GOPTS_MSTI,
 	__BRIDGE_VLANDB_GOPTS_MAX
 };
 #define BRIDGE_VLANDB_GOPTS_MAX (__BRIDGE_VLANDB_GOPTS_MAX - 1)
@@ -759,6 +776,7 @@ struct br_mcast_stats {
 enum br_boolopt_id {
 	BR_BOOLOPT_NO_LL_LEARN,
 	BR_BOOLOPT_MCAST_VLAN_SNOOPING,
+	BR_BOOLOPT_MST_ENABLE,
 	BR_BOOLOPT_MAX
 };
 
diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h
index 51530aade46e..83849a37db5b 100644
--- a/include/uapi/linux/rtnetlink.h
+++ b/include/uapi/linux/rtnetlink.h
@@ -817,6 +817,7 @@ enum {
 #define RTEXT_FILTER_MRP	(1 << 4)
 #define RTEXT_FILTER_CFM_CONFIG	(1 << 5)
 #define RTEXT_FILTER_CFM_STATUS	(1 << 6)
+#define RTEXT_FILTER_MST	(1 << 7)
 
 /* End of information exported to user level */