net: don't reforward packets already forwarded by offload device

Just before queuing skb for xmit on port, check if skb has been marked by
switchdev port driver as already fordwarded by device.  If so, drop skb.  A
non-zero skb->offload_fwd_mark field is set by the switchdev port
driver/device on ingress to indicate the skb has already been forwarded by
the device to egress ports with matching dev->skb_mark.  The switchdev port
driver would assign a non-zero dev->offload_skb_mark for each device port
netdev during registration, for example.
Signed-off-by: NScott Feldman <sfeldma@gmail.com>
Acked-by: NJiri Pirko <jiri@resnulli.us>
Acked-by: NRoopa Prabhu <roopa@cumulusnetworks.com>
Acked-by: NNicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

include/linux/netdevice.h

@@ -1456,6 +1456,8 @@ enum netdev_priv_flags {
  *
  *	@xps_maps:	XXX: need comments on this one
  *
+ *	@offload_fwd_mark:	Offload device fwding mark
+ *
  *	@trans_start:		Time (in jiffies) of last Tx
  *	@watchdog_timeo:	Represents the timeout that is used by
  *				the watchdog ( see dev_watchdog() )
@@ -1697,6 +1699,10 @@ struct net_device {
 	struct xps_dev_maps __rcu *xps_maps;
 #endif
 
+#ifdef CONFIG_NET_SWITCHDEV
+	u32			offload_fwd_mark;
+#endif
+
 	/* These may be needed for future network-power-down code. */
 
 	/*

include/linux/skbuff.h

@@ -506,6 +506,7 @@ static inline u32 skb_mstamp_us_delta(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
@@ -650,9 +651,15 @@ 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;
 		__u32		reserved_tailroom;

net/core/dev.c

@@ -3061,6 +3061,16 @@ static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv)
 	else
 		skb_dst_force(skb);
 
+#ifdef CONFIG_NET_SWITCHDEV
+	/* Don't forward if offload device already forwarded */
+	if (skb->offload_fwd_mark &&
+	    skb->offload_fwd_mark == dev->offload_fwd_mark) {
+		consume_skb(skb);
+		rc = NET_XMIT_SUCCESS;
+		goto out;
+	}
+#endif
+
 	txq = netdev_pick_tx(dev, skb, accel_priv);
 	q = rcu_dereference_bh(txq->qdisc);