bridge: switchdev: Add forward mark support for stacked devices

switchdev_port_fwd_mark_set() is used to set the 'offload_fwd_mark' of
port netdevs so that packets being flooded by the device won't be
flooded twice.

It works by assigning a unique identifier (the ifindex of the first
bridge port) to bridge ports sharing the same parent ID. This prevents
packets from being flooded twice by the same switch, but will flood
packets through bridge ports belonging to a different switch.

This method is problematic when stacked devices are taken into account,
such as VLANs. In such cases, a physical port netdev can have upper
devices being members in two different bridges, thus requiring two
different 'offload_fwd_mark's to be configured on the port netdev, which
is impossible.

The main problem is that packet and netdev marking is performed at the
physical netdev level, whereas flooding occurs between bridge ports,
which are not necessarily port netdevs.

Instead, packet and netdev marking should really be done in the bridge
driver with the switch driver only telling it which packets it already
forwarded. The bridge driver will mark such packets using the mark
assigned to the ingress bridge port and will prevent the packet from
being forwarded through any bridge port sharing the same mark (i.e.
having the same parent ID).

Remove the current switchdev 'offload_fwd_mark' implementation and
instead implement the proposed method. In addition, make rocker - the
sole user of the mark - use the proposed method.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 5 insertions, 19 deletions

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 794bb0733799..d122be9345c7 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1562,8 +1562,6 @@ enum netdev_priv_flags {
  *
  *	@xps_maps:	XXX: need comments on this one
  *
- *	@offload_fwd_mark:	Offload device fwding mark
- *
  *	@watchdog_timeo:	Represents the timeout that is used by
  *				the watchdog (see dev_watchdog())
  *	@watchdog_timer:	List of timers
@@ -1814,9 +1812,6 @@ struct net_device {
 #ifdef CONFIG_NET_CLS_ACT
 	struct tcf_proto __rcu  *egress_cl_list;
 #endif
-#ifdef CONFIG_NET_SWITCHDEV
-	u32			offload_fwd_mark;
-#endif
 
 	/* These may be needed for future network-power-down code. */
 	struct timer_list	watchdog_timer;
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 7047448e8129..cfb7219be665 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -612,7 +612,6 @@ static inline bool skb_mstamp_after(const struct skb_mstamp *t1,
  *	@no_fcs:  Request NIC to treat last 4 bytes as Ethernet FCS
   *	@napi_id: id of the NAPI struct this skb came from
  *	@secmark: security marking
- *	@offload_fwd_mark: fwding offload mark
  *	@mark: Generic packet mark
  *	@vlan_proto: vlan encapsulation protocol
  *	@vlan_tci: vlan tag control information
@@ -730,7 +729,10 @@ struct sk_buff {
 	__u8			ipvs_property:1;
 	__u8			inner_protocol_type:1;
 	__u8			remcsum_offload:1;
-	/* 3 or 5 bit hole */
+#ifdef CONFIG_NET_SWITCHDEV
+	__u8			offload_fwd_mark:1;
+#endif
+	/* 2, 4 or 5 bit hole */
 
 #ifdef CONFIG_NET_SCHED
 	__u16			tc_index;	/* traffic control index */
@@ -757,14 +759,9 @@ struct sk_buff {
 		unsigned int	sender_cpu;
 	};
 #endif
-	union {
 #ifdef CONFIG_NETWORK_SECMARK
-		__u32		secmark;
+	__u32		secmark;
 #endif
-#ifdef CONFIG_NET_SWITCHDEV
-		__u32		offload_fwd_mark;
-#endif
-	};
 
 	union {
 		__u32		mark;
diff --git a/include/net/switchdev.h b/include/net/switchdev.h
index 62f6a967a1b7..82f5e0462021 100644
--- a/include/net/switchdev.h
+++ b/include/net/switchdev.h
@@ -347,12 +347,6 @@ static inline int switchdev_port_fdb_dump(struct sk_buff *skb,
        return idx;
 }
 
-static inline void switchdev_port_fwd_mark_set(struct net_device *dev,
-					       struct net_device *group_dev,
-					       bool joining)
-{
-}
-
 static inline bool switchdev_port_same_parent_id(struct net_device *a,
 						 struct net_device *b)
 {