Merge branch 'mlxsw-fw-mark-offload'

Jiri Pirko says:

====================
mlxsw: Introduce support for offload forward mark

Ido says:
This patchset enables the forwarding of certain control packets by the
device instead of relying on the CPU to do the forwarding.

The first two patches simplify the current switchdev offload forward
infrastructure and make it usable for stacked devices. This is done by
moving the packet and port marking to the bridge driver instead of the
switch driver.

Patches 3-5 add the mlxsw specific bits to support the forward mark.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

Documentation/networking/switchdev.txt

@@ -283,15 +283,10 @@ be sent to the port netdev for processing by the bridge driver.  The
 bridge should not reflood the packet to the same ports the device flooded,
 otherwise there will be duplicate packets on the wire.
 
-To avoid duplicate packets, the device/driver should mark a packet as already
-forwarded using skb->offload_fwd_mark.  The same mark is set on the device
-ports in the domain using dev->offload_fwd_mark.  If the skb->offload_fwd_mark
-is non-zero and matches the forwarding egress port's dev->skb_mark, the kernel
-will drop the skb right before transmit on the egress port, with the
-understanding that the device already forwarded the packet on same egress port.
-The driver can use switchdev_port_fwd_mark_set() to set a globally unique mark
-for port's dev->offload_fwd_mark, based on the port's parent ID (switch ID) and
-a group ifindex.
+To avoid duplicate packets, the switch driver should mark a packet as already
+forwarded by setting the skb->offload_fwd_mark bit. The bridge driver will mark
+the skb using the ingress bridge port's mark and prevent it from being forwarded
+through any bridge port with the same mark.
 
 It is possible for the switch device to not handle flooding and push the
 packets up to the bridge driver for flooding.  This is not ideal as the number

drivers/net/ethernet/mellanox/mlxsw/core.h

@@ -87,6 +87,7 @@ struct mlxsw_rx_listener {
 	void (*func)(struct sk_buff *skb, u8 local_port, void *priv);
 	u8 local_port;
 	u16 trap_id;
+	enum mlxsw_reg_hpkt_action action;
 };
 
 struct mlxsw_event_listener {

drivers/net/ethernet/mellanox/mlxsw/spectrum.c

@@ -2570,123 +2570,47 @@ static void mlxsw_sp_rx_listener_func(struct sk_buff *skb, u8 local_port,
 	netif_receive_skb(skb);
 }
 
+static void mlxsw_sp_rx_listener_mark_func(struct sk_buff *skb, u8 local_port,
+					   void *priv)
+{
+	skb->offload_fwd_mark = 1;
+	return mlxsw_sp_rx_listener_func(skb, local_port, priv);
+}
+
+#define MLXSW_SP_RXL(_func, _trap_id, _action)			\
+	{							\
+		.func = _func,					\
+		.local_port = MLXSW_PORT_DONT_CARE,		\
+		.trap_id = MLXSW_TRAP_ID_##_trap_id,		\
+		.action = MLXSW_REG_HPKT_ACTION_##_action,	\
+	}
+
 static const struct mlxsw_rx_listener mlxsw_sp_rx_listener[] = {
-	{
-		.func = mlxsw_sp_rx_listener_func,
-		.local_port = MLXSW_PORT_DONT_CARE,
-		.trap_id = MLXSW_TRAP_ID_FDB_MC,
-	},
+	MLXSW_SP_RXL(mlxsw_sp_rx_listener_func, FDB_MC, TRAP_TO_CPU),
 	/* Traps for specific L2 packet types, not trapped as FDB MC */
-	{
-		.func = mlxsw_sp_rx_listener_func,
-		.local_port = MLXSW_PORT_DONT_CARE,
-		.trap_id = MLXSW_TRAP_ID_STP,
-	},
-	{
-		.func = mlxsw_sp_rx_listener_func,
-		.local_port = MLXSW_PORT_DONT_CARE,
-		.trap_id = MLXSW_TRAP_ID_LACP,
-	},
-	{
-		.func = mlxsw_sp_rx_listener_func,
-		.local_port = MLXSW_PORT_DONT_CARE,
-		.trap_id = MLXSW_TRAP_ID_EAPOL,
-	},
-	{
-		.func = mlxsw_sp_rx_listener_func,
-		.local_port = MLXSW_PORT_DONT_CARE,
-		.trap_id = MLXSW_TRAP_ID_LLDP,
-	},
-	{
-		.func = mlxsw_sp_rx_listener_func,
-		.local_port = MLXSW_PORT_DONT_CARE,
-		.trap_id = MLXSW_TRAP_ID_MMRP,
-	},
-	{
-		.func = mlxsw_sp_rx_listener_func,
-		.local_port = MLXSW_PORT_DONT_CARE,
-		.trap_id = MLXSW_TRAP_ID_MVRP,
-	},
-	{
-		.func = mlxsw_sp_rx_listener_func,
-		.local_port = MLXSW_PORT_DONT_CARE,
-		.trap_id = MLXSW_TRAP_ID_RPVST,
-	},
-	{
-		.func = mlxsw_sp_rx_listener_func,
-		.local_port = MLXSW_PORT_DONT_CARE,
-		.trap_id = MLXSW_TRAP_ID_DHCP,
-	},
-	{
-		.func = mlxsw_sp_rx_listener_func,
-		.local_port = MLXSW_PORT_DONT_CARE,
-		.trap_id = MLXSW_TRAP_ID_IGMP_QUERY,
-	},
-	{
-		.func = mlxsw_sp_rx_listener_func,
-		.local_port = MLXSW_PORT_DONT_CARE,
-		.trap_id = MLXSW_TRAP_ID_IGMP_V1_REPORT,
-	},
-	{
-		.func = mlxsw_sp_rx_listener_func,
-		.local_port = MLXSW_PORT_DONT_CARE,
-		.trap_id = MLXSW_TRAP_ID_IGMP_V2_REPORT,
-	},
-	{
-		.func = mlxsw_sp_rx_listener_func,
-		.local_port = MLXSW_PORT_DONT_CARE,
-		.trap_id = MLXSW_TRAP_ID_IGMP_V2_LEAVE,
-	},
-	{
-		.func = mlxsw_sp_rx_listener_func,
-		.local_port = MLXSW_PORT_DONT_CARE,
-		.trap_id = MLXSW_TRAP_ID_IGMP_V3_REPORT,
-	},
-	{
-		.func = mlxsw_sp_rx_listener_func,
-		.local_port = MLXSW_PORT_DONT_CARE,
-		.trap_id = MLXSW_TRAP_ID_ARPBC,
-	},
-	{
-		.func = mlxsw_sp_rx_listener_func,
-		.local_port = MLXSW_PORT_DONT_CARE,
-		.trap_id = MLXSW_TRAP_ID_ARPUC,
-	},
-	{
-		.func = mlxsw_sp_rx_listener_func,
-		.local_port = MLXSW_PORT_DONT_CARE,
-		.trap_id = MLXSW_TRAP_ID_MTUERROR,
-	},
-	{
-		.func = mlxsw_sp_rx_listener_func,
-		.local_port = MLXSW_PORT_DONT_CARE,
-		.trap_id = MLXSW_TRAP_ID_TTLERROR,
-	},
-	{
-		.func = mlxsw_sp_rx_listener_func,
-		.local_port = MLXSW_PORT_DONT_CARE,
-		.trap_id = MLXSW_TRAP_ID_LBERROR,
-	},
-	{
-		.func = mlxsw_sp_rx_listener_func,
-		.local_port = MLXSW_PORT_DONT_CARE,
-		.trap_id = MLXSW_TRAP_ID_OSPF,
-	},
-	{
-		.func = mlxsw_sp_rx_listener_func,
-		.local_port = MLXSW_PORT_DONT_CARE,
-		.trap_id = MLXSW_TRAP_ID_IP2ME,
-	},
-	{
-		.func = mlxsw_sp_rx_listener_func,
-		.local_port = MLXSW_PORT_DONT_CARE,
-		.trap_id = MLXSW_TRAP_ID_RTR_INGRESS0,
-	},
-	{
-		.func = mlxsw_sp_rx_listener_func,
-		.local_port = MLXSW_PORT_DONT_CARE,
-		.trap_id = MLXSW_TRAP_ID_HOST_MISS_IPV4,
-	},
+	MLXSW_SP_RXL(mlxsw_sp_rx_listener_func, STP, TRAP_TO_CPU),
+	MLXSW_SP_RXL(mlxsw_sp_rx_listener_func, LACP, TRAP_TO_CPU),
+	MLXSW_SP_RXL(mlxsw_sp_rx_listener_func, EAPOL, TRAP_TO_CPU),
+	MLXSW_SP_RXL(mlxsw_sp_rx_listener_func, LLDP, TRAP_TO_CPU),
+	MLXSW_SP_RXL(mlxsw_sp_rx_listener_func, MMRP, TRAP_TO_CPU),
+	MLXSW_SP_RXL(mlxsw_sp_rx_listener_func, MVRP, TRAP_TO_CPU),
+	MLXSW_SP_RXL(mlxsw_sp_rx_listener_func, RPVST, TRAP_TO_CPU),
+	MLXSW_SP_RXL(mlxsw_sp_rx_listener_mark_func, DHCP, MIRROR_TO_CPU),
+	MLXSW_SP_RXL(mlxsw_sp_rx_listener_mark_func, IGMP_QUERY, MIRROR_TO_CPU),
+	MLXSW_SP_RXL(mlxsw_sp_rx_listener_func, IGMP_V1_REPORT, TRAP_TO_CPU),
+	MLXSW_SP_RXL(mlxsw_sp_rx_listener_func, IGMP_V2_REPORT, TRAP_TO_CPU),
+	MLXSW_SP_RXL(mlxsw_sp_rx_listener_func, IGMP_V2_LEAVE, TRAP_TO_CPU),
+	MLXSW_SP_RXL(mlxsw_sp_rx_listener_func, IGMP_V3_REPORT, TRAP_TO_CPU),
+	MLXSW_SP_RXL(mlxsw_sp_rx_listener_mark_func, ARPBC, MIRROR_TO_CPU),
+	MLXSW_SP_RXL(mlxsw_sp_rx_listener_mark_func, ARPUC, MIRROR_TO_CPU),
+	/* L3 traps */
+	MLXSW_SP_RXL(mlxsw_sp_rx_listener_func, MTUERROR, TRAP_TO_CPU),
+	MLXSW_SP_RXL(mlxsw_sp_rx_listener_func, TTLERROR, TRAP_TO_CPU),
+	MLXSW_SP_RXL(mlxsw_sp_rx_listener_func, LBERROR, TRAP_TO_CPU),
+	MLXSW_SP_RXL(mlxsw_sp_rx_listener_mark_func, OSPF, TRAP_TO_CPU),
+	MLXSW_SP_RXL(mlxsw_sp_rx_listener_func, IP2ME, TRAP_TO_CPU),
+	MLXSW_SP_RXL(mlxsw_sp_rx_listener_func, RTR_INGRESS0, TRAP_TO_CPU),
+	MLXSW_SP_RXL(mlxsw_sp_rx_listener_func, HOST_MISS_IPV4, TRAP_TO_CPU),
 };
 
 static int mlxsw_sp_traps_init(struct mlxsw_sp *mlxsw_sp)
@@ -2713,7 +2637,7 @@ static int mlxsw_sp_traps_init(struct mlxsw_sp *mlxsw_sp)
 		if (err)
 			goto err_rx_listener_register;
 
-		mlxsw_reg_hpkt_pack(hpkt_pl, MLXSW_REG_HPKT_ACTION_TRAP_TO_CPU,
+		mlxsw_reg_hpkt_pack(hpkt_pl, mlxsw_sp_rx_listener[i].action,
 				    mlxsw_sp_rx_listener[i].trap_id);
 		err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(hpkt), hpkt_pl);
 		if (err)

drivers/net/ethernet/rocker/rocker_main.c

@@ -2412,7 +2412,7 @@ static int rocker_port_rx_proc(const struct rocker *rocker,
 	skb->protocol = eth_type_trans(skb, rocker_port->dev);
 
 	if (rx_flags & ROCKER_RX_FLAGS_FWD_OFFLOAD)
-		skb->offload_fwd_mark = rocker_port->dev->offload_fwd_mark;
+		skb->offload_fwd_mark = 1;
 
 	rocker_port->dev->stats.rx_packets++;
 	rocker_port->dev->stats.rx_bytes += skb->len;

drivers/net/ethernet/rocker/rocker_ofdpa.c

@@ -2558,7 +2558,6 @@ static int ofdpa_port_init(struct rocker_port *rocker_port)
 	struct ofdpa_port *ofdpa_port = rocker_port->wpriv;
 	int err;
 
-	switchdev_port_fwd_mark_set(ofdpa_port->dev, NULL, false);
 	rocker_port_set_learning(rocker_port,
 				 !!(ofdpa_port->brport_flags & BR_LEARNING));
 
@@ -2817,7 +2816,6 @@ static int ofdpa_port_bridge_join(struct ofdpa_port *ofdpa_port,
 		ofdpa_port_internal_vlan_id_get(ofdpa_port, bridge->ifindex);
 
 	ofdpa_port->bridge_dev = bridge;
-	switchdev_port_fwd_mark_set(ofdpa_port->dev, bridge, true);
 
 	return ofdpa_port_vlan_add(ofdpa_port, NULL, OFDPA_UNTAGGED_VID, 0);
 }
@@ -2836,8 +2834,6 @@ static int ofdpa_port_bridge_leave(struct ofdpa_port *ofdpa_port)
 		ofdpa_port_internal_vlan_id_get(ofdpa_port,
 						ofdpa_port->dev->ifindex);
 
-	switchdev_port_fwd_mark_set(ofdpa_port->dev, ofdpa_port->bridge_dev,
-				    false);
 	ofdpa_port->bridge_dev = NULL;
 
 	err = ofdpa_port_vlan_add(ofdpa_port, NULL, OFDPA_UNTAGGED_VID, 0);

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;

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;

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)
 {

net/bridge/Makefile

@@ -20,4 +20,6 @@ bridge-$(CONFIG_BRIDGE_IGMP_SNOOPING) += br_multicast.o br_mdb.o
 
 bridge-$(CONFIG_BRIDGE_VLAN_FILTERING) += br_vlan.o
 
+bridge-$(CONFIG_NET_SWITCHDEV) += br_switchdev.o
+
 obj-$(CONFIG_NETFILTER) += netfilter/

net/bridge/br_forward.c

@@ -29,7 +29,8 @@ static inline int should_deliver(const struct net_bridge_port *p,
 
 	vg = nbp_vlan_group_rcu(p);
 	return ((p->flags & BR_HAIRPIN_MODE) || skb->dev != p->dev) &&
-		br_allowed_egress(vg, skb) && p->state == BR_STATE_FORWARDING;
+		br_allowed_egress(vg, skb) && p->state == BR_STATE_FORWARDING &&
+		nbp_switchdev_allowed_egress(p, skb);
 }
 
 int br_dev_queue_push_xmit(struct net *net, struct sock *sk, struct sk_buff *skb)

net/bridge/br_if.c

@@ -545,6 +545,10 @@ int br_add_if(struct net_bridge *br, struct net_device *dev)
 	if (err)
 		goto err5;
 
+	err = nbp_switchdev_mark_set(p);
+	if (err)
+		goto err6;
+
 	dev_disable_lro(dev);
 
 	list_add_rcu(&p->list, &br->port_list);
@@ -566,7 +570,7 @@ int br_add_if(struct net_bridge *br, struct net_device *dev)
 	err = nbp_vlan_init(p);
 	if (err) {
 		netdev_err(dev, "failed to initialize vlan filtering on this port\n");
-		goto err6;
+		goto err7;
 	}
 
 	spin_lock_bh(&br->lock);
@@ -589,12 +593,12 @@ int br_add_if(struct net_bridge *br, struct net_device *dev)
 
 	return 0;
 
-err6:
+err7:
 	list_del_rcu(&p->list);
 	br_fdb_delete_by_port(br, p, 0, 1);
 	nbp_update_port_count(br);
+err6:
 	netdev_upper_dev_unlink(dev, br->dev);
-
 err5:
 	dev->priv_flags &= ~IFF_BRIDGE_PORT;
 	netdev_rx_handler_unregister(dev);

net/bridge/br_input.c

@@ -145,6 +145,8 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb
 	if (!br_allowed_ingress(p->br, nbp_vlan_group_rcu(p), skb, &vid))
 		goto out;
 
+	nbp_switchdev_frame_mark(p, skb);
+
 	/* insert into forwarding database after filtering to avoid spoofing */
 	br = p->br;
 	if (p->flags & BR_LEARNING)